qqtang/sskj
1
3
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update(P800/GLM5.2): 单节点部署测试脚本

Browse Source
This commit is contained in:
Spike 2026-08-19 02:24:17 +00:00
parent 987f1db4b0
commit eeec56c2cf
45 changed files with 2544 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
experiments/p800/glm52_w4a8_sglang_tp8_single_node/README.md Normal file
View File

@ -0,0 +1,11 @@
# GLM-5.2 W4A8 P800 single-node smoke benchmark
- Host: `sskj-P800-4` (`gpu051`)
- Image: `iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746`
- Model: `/data2/GLM-5.2-w4a8`
- Parallelism: TP=8, EP=8, DP=1
- Quantization: `w4a8_int4`; KV cache: `int8`
- Dataset: `/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json`
- Benchmark: ShareGPT, 64 prompts, concurrency 8, output length 128, request rate unlimited
Run `bash start_glm52_w4a8.sh`, wait for `http://127.0.0.1:30000/health`, then run `bash run_bench.sh`.

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-1555-sharegpt-c8-o128/bench_sharegpt_c8_o128.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

231
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-1555-sharegpt-c8-o128/container_inspect.json Normal file
View File

@ -0,0 +1,231 @@
[
{
"Id": "5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180",
"Created": "2026-08-17T15:52:21.087868771Z",
"Path": "bash",
"Args": [
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"State": {
"Status": "running",
"Running": true,
"Paused": false,
"Restarting": false,
"OOMKilled": false,
"Dead": false,
"Pid": 137722,
"ExitCode": 0,
"Error": "",
"StartedAt": "2026-08-17T15:52:21.126324465Z",
"FinishedAt": "0001-01-01T00:00:00Z"
},
"Image": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"ResolvConfPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/resolv.conf",
"HostnamePath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/hostname",
"HostsPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/hosts",
"LogPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180-json.log",
"Name": "/glm52-w4a8-tp8",
"RestartCount": 0,
"Driver": "overlayfs",
"Platform": "linux",
"MountLabel": "",
"ProcessLabel": "",
"AppArmorProfile": "unconfined",
"ExecIDs": null,
"HostConfig": {
"Binds": [
"/data2/GLM-5.2-w4a8:/models:ro",
"/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json:/workspace/ShareGPT_V3_unfiltered_cleaned_split.json:ro",
"/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke:/workspace/run"
],
"ContainerIDFile": "",
"LogConfig": {
"Type": "json-file",
"Config": {}
},
"NetworkMode": "host",
"PortBindings": {},
"RestartPolicy": {
"Name": "no",
"MaximumRetryCount": 0
},
"AutoRemove": false,
"VolumeDriver": "",
"VolumesFrom": null,
"ConsoleSize": [
0,
0
],
"CapAdd": null,
"CapDrop": null,
"CgroupnsMode": "private",
"Dns": null,
"DnsOptions": [],
"DnsSearch": [],
"ExtraHosts": null,
"GroupAdd": null,
"IpcMode": "host",
"Cgroup": "",
"Links": null,
"OomScoreAdj": 0,
"PidMode": "",
"Privileged": true,
"PublishAllPorts": false,
"ReadonlyRootfs": false,
"SecurityOpt": [
"seccomp=unconfined",
"label=disable"
],
"UTSMode": "host",
"UsernsMode": "",
"ShmSize": 274877906944,
"Runtime": "runc",
"Isolation": "",
"CpuShares": 0,
"Memory": 0,
"NanoCpus": 0,
"CgroupParent": "",
"BlkioWeight": 0,
"BlkioWeightDevice": [],
"BlkioDeviceReadBps": [],
"BlkioDeviceWriteBps": [],
"BlkioDeviceReadIOps": [],
"BlkioDeviceWriteIOps": [],
"CpuPeriod": 0,
"CpuQuota": 0,
"CpuRealtimePeriod": 0,
"CpuRealtimeRuntime": 0,
"CpusetCpus": "",
"CpusetMems": "",
"Devices": [],
"DeviceCgroupRules": null,
"DeviceRequests": null,
"MemoryReservation": 0,
"MemorySwap": 0,
"MemorySwappiness": null,
"OomKillDisable": null,
"PidsLimit": null,
"Ulimits": [
{
"Name": "core",
"Hard": -1,
"Soft": -1
}
],
"CpuCount": 0,
"CpuPercent": 0,
"IOMaximumIOps": 0,
"IOMaximumBandwidth": 0,
"MaskedPaths": null,
"ReadonlyPaths": null
},
"Storage": {
"RootFS": {
"Snapshot": {
"Name": "overlayfs"
}
}
},
"Mounts": [
{
"Type": "bind",
"Source": "/data2/GLM-5.2-w4a8",
"Destination": "/models",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
"Destination": "/workspace/ShareGPT_V3_unfiltered_cleaned_split.json",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke",
"Destination": "/workspace/run",
"Mode": "",
"RW": true,
"Propagation": "rprivate"
}
],
"Config": {
"Hostname": "gpu051",
"Domainname": "",
"User": "",
"AttachStdin": false,
"AttachStdout": false,
"AttachStderr": false,
"Tty": false,
"OpenStdin": false,
"StdinOnce": false,
"Env": [
"CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"XPU_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"CUDA_DISABLE_PRINTF=1",
"GLOO_SOCKET_TIMEOUT=60000",
"PATH=/root/miniconda/envs/python310_torch25_cuda/lib/python3.10/site-packages/torch_xmlir/xre/bin/:/root/miniconda/bin:/root/.cargo/bin:/usr/local/go/bin:/usr/local/cuda-11.7/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
"TZ=Asia/Shanghai",
"LANG=zh_CN.UTF-8"
],
"Cmd": [
"bash",
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"Image": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"Volumes": null,
"WorkingDir": "/workspace/run",
"Entrypoint": null,
"Labels": {
"autofix_time": "2025-12-03T10:19:26",
"description": "infer_ubuntu2204_dev runtime + miniconda",
"maintainer": "wenli <wenli01@baidu.com>",
"org.opencontainers.image.ref.name": "ubuntu",
"org.opencontainers.image.version": "22.04",
"version": "infer_ubuntu2204_dev:miniconda_0.1"
}
},
"NetworkSettings": {
"SandboxID": "81c79e65bbac2dcf756cbff44c4a0ba01bd8be20cc29b1b7907701dfb0a30619",
"SandboxKey": "/var/run/docker/netns/default",
"Ports": {},
"Networks": {
"host": {
"IPAMConfig": null,
"Links": null,
"Aliases": null,
"DriverOpts": null,
"GwPriority": 0,
"NetworkID": "0e3fdd7bc7639e6dc911f6f09344de480a35fa47ce2e83ff21a8160e319f48ac",
"EndpointID": "35fe2742654dbbedd58999151fd8a77234c95ea9204ebd61074cd27d27d85871",
"Gateway": "",
"IPAddress": "",
"MacAddress": "",
"IPPrefixLen": 0,
"IPv6Gateway": "",
"GlobalIPv6Address": "",
"GlobalIPv6PrefixLen": 0,
"DNSNames": null
}
}
},
"ImageManifestDescriptor": {
"mediaType": "application/vnd.oci.image.manifest.v1+json",
"digest": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"size": 3632,
"annotations": {
"io.containerd.image.name": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"org.opencontainers.image.ref.name": "20260715_5746"
},
"platform": {
"architecture": "amd64",
"os": "linux"
}
}
}
]

111
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-1555-sharegpt-c8-o128/xpu_after_bench.txt Normal file
View File

@ -0,0 +1,111 @@
Mon Aug 17 15:56:53 2026
+-----------------------------------------------------------------------------+
| XPU-SMI Driver Version: 5.19.0.0 XPU-RT Version: 5.19.0 |
|-------------------------------+----------------------+----------------------+
| XPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | XPU-Util Compute M. |
| | L3-Usage | SR-IOV M. |
|===============================+======================+======================|
| 0 P800 OAM N/A | 00000000:03:00.0 N/A | 0 |
| N/A 42C N/A 89W / 400W | 87958MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 1 P800 OAM N/A | 00000000:05:00.0 N/A | 0 |
| N/A 46C N/A 90W / 400W | 87958MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 2 P800 OAM N/A | 00000000:63:00.0 N/A | 0 |
| N/A 41C N/A 90W / 400W | 87958MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 3 P800 OAM N/A | 00000000:65:00.0 N/A | 0 |
| N/A 47C N/A 90W / 400W | 87958MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 4 P800 OAM N/A | 00000000:83:00.0 N/A | 0 |
| N/A 41C N/A 86W / 400W | 88310MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 5 P800 OAM N/A | 00000000:85:00.0 N/A | 0 |
| N/A 47C N/A 88W / 400W | 87958MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 6 P800 OAM N/A | 00000000:A3:00.0 N/A | 0 |
| N/A 43C N/A 89W / 400W | 87914MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 7 P800 OAM N/A | 00000000:A5:00.0 N/A | 0 |
| N/A 50C N/A 90W / 400W | 88292MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| XPU XI CI PID Type Process name XPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 0 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 0 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 0 N/A N/A 137943 C sglang::scheduler_TP3_EP3 87826MiB |
| 0 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 0 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 0 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 0 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 1 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 1 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 1 N/A N/A 137942 C sglang::scheduler_TP2_EP2 87826MiB |
| 1 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 1 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 1 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 1 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 1 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 2 N/A N/A 137940 C sglang::scheduler_TP0_EP0 87826MiB |
| 2 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 2 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 2 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 2 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 2 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 2 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 2 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 3 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 3 N/A N/A 137941 C sglang::scheduler_TP1_EP1 87826MiB |
| 3 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 3 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 3 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 3 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 3 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 3 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 4 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 4 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 4 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 4 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 4 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 4 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 4 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 4 N/A N/A 137947 C sglang::scheduler_TP7_EP7 88178MiB |
| 5 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 5 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 5 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 5 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 5 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 5 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 5 N/A N/A 137946 C sglang::scheduler_TP6_EP6 87826MiB |
| 5 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 6 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 6 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 6 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 6 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 6 N/A N/A 137944 C sglang::scheduler_TP4_EP4 87782MiB |
| 6 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 6 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 6 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 7 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 7 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 7 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 7 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 7 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 7 N/A N/A 137945 C sglang::scheduler_TP5_EP5 88160MiB |
| 7 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 7 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
+-----------------------------------------------------------------------------+

111
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-1555-sharegpt-c8-o128/xpu_before_bench.txt Normal file
View File

@ -0,0 +1,111 @@
Mon Aug 17 15:55:17 2026
+-----------------------------------------------------------------------------+
| XPU-SMI Driver Version: 5.19.0.0 XPU-RT Version: 5.19.0 |
|-------------------------------+----------------------+----------------------+
| XPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | XPU-Util Compute M. |
| | L3-Usage | SR-IOV M. |
|===============================+======================+======================|
| 0 P800 OAM N/A | 00000000:03:00.0 N/A | 0 |
| N/A 39C N/A 88W / 400W | 85774MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 1 P800 OAM N/A | 00000000:05:00.0 N/A | 0 |
| N/A 43C N/A 89W / 400W | 85774MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 2 P800 OAM N/A | 00000000:63:00.0 N/A | 0 |
| N/A 38C N/A 90W / 400W | 85774MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 3 P800 OAM N/A | 00000000:65:00.0 N/A | 0 |
| N/A 43C N/A 93W / 400W | 85774MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 4 P800 OAM N/A | 00000000:83:00.0 N/A | 0 |
| N/A 39C N/A 86W / 400W | 85774MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 5 P800 OAM N/A | 00000000:85:00.0 N/A | 0 |
| N/A 43C N/A 91W / 400W | 85774MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 6 P800 OAM N/A | 00000000:A3:00.0 N/A | 0 |
| N/A 41C N/A 89W / 400W | 85774MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 7 P800 OAM N/A | 00000000:A5:00.0 N/A | 0 |
| N/A 47C N/A 89W / 400W | 85772MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| XPU XI CI PID Type Process name XPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 0 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 0 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 0 N/A N/A 137943 C sglang::scheduler_TP3_EP3 85642MiB |
| 0 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 0 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 0 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 0 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 1 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 1 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 1 N/A N/A 137942 C sglang::scheduler_TP2_EP2 85642MiB |
| 1 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 1 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 1 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 1 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 1 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 2 N/A N/A 137940 C sglang::scheduler_TP0_EP0 85642MiB |
| 2 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 2 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 2 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 2 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 2 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 2 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 2 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 3 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 3 N/A N/A 137941 C sglang::scheduler_TP1_EP1 85642MiB |
| 3 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 3 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 3 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 3 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 3 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 3 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 4 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 4 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 4 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 4 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 4 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 4 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 4 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 4 N/A N/A 137947 C sglang::scheduler_TP7_EP7 85642MiB |
| 5 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 5 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 5 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 5 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 5 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 5 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 5 N/A N/A 137946 C sglang::scheduler_TP6_EP6 85642MiB |
| 5 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 6 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 6 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 6 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 6 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 6 N/A N/A 137944 C sglang::scheduler_TP4_EP4 85642MiB |
| 6 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 6 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 6 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 7 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 7 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 7 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 7 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 7 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 7 N/A N/A 137945 C sglang::scheduler_TP5_EP5 85640MiB |
| 7 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 7 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
+-----------------------------------------------------------------------------+

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-sharegpt-c1-c32-sweep/bench_sharegpt_c16_o128.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-sharegpt-c1-c32-sweep/bench_sharegpt_c1_o128.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-sharegpt-c1-c32-sweep/bench_sharegpt_c2_o128.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-sharegpt-c1-c32-sweep/bench_sharegpt_c32_o128.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-sharegpt-c1-c32-sweep/bench_sharegpt_c4_o128.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-sharegpt-c1-c32-sweep/bench_sharegpt_c8_o128.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

231
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-sharegpt-c1-c32-sweep/container_inspect.json Normal file
View File

@ -0,0 +1,231 @@
[
{
"Id": "5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180",
"Created": "2026-08-17T15:52:21.087868771Z",
"Path": "bash",
"Args": [
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"State": {
"Status": "running",
"Running": true,
"Paused": false,
"Restarting": false,
"OOMKilled": false,
"Dead": false,
"Pid": 137722,
"ExitCode": 0,
"Error": "",
"StartedAt": "2026-08-17T15:52:21.126324465Z",
"FinishedAt": "0001-01-01T00:00:00Z"
},
"Image": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"ResolvConfPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/resolv.conf",
"HostnamePath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/hostname",
"HostsPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/hosts",
"LogPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180-json.log",
"Name": "/glm52-w4a8-tp8",
"RestartCount": 0,
"Driver": "overlayfs",
"Platform": "linux",
"MountLabel": "",
"ProcessLabel": "",
"AppArmorProfile": "unconfined",
"ExecIDs": null,
"HostConfig": {
"Binds": [
"/data2/GLM-5.2-w4a8:/models:ro",
"/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json:/workspace/ShareGPT_V3_unfiltered_cleaned_split.json:ro",
"/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke:/workspace/run"
],
"ContainerIDFile": "",
"LogConfig": {
"Type": "json-file",
"Config": {}
},
"NetworkMode": "host",
"PortBindings": {},
"RestartPolicy": {
"Name": "no",
"MaximumRetryCount": 0
},
"AutoRemove": false,
"VolumeDriver": "",
"VolumesFrom": null,
"ConsoleSize": [
0,
0
],
"CapAdd": null,
"CapDrop": null,
"CgroupnsMode": "private",
"Dns": null,
"DnsOptions": [],
"DnsSearch": [],
"ExtraHosts": null,
"GroupAdd": null,
"IpcMode": "host",
"Cgroup": "",
"Links": null,
"OomScoreAdj": 0,
"PidMode": "",
"Privileged": true,
"PublishAllPorts": false,
"ReadonlyRootfs": false,
"SecurityOpt": [
"seccomp=unconfined",
"label=disable"
],
"UTSMode": "host",
"UsernsMode": "",
"ShmSize": 274877906944,
"Runtime": "runc",
"Isolation": "",
"CpuShares": 0,
"Memory": 0,
"NanoCpus": 0,
"CgroupParent": "",
"BlkioWeight": 0,
"BlkioWeightDevice": [],
"BlkioDeviceReadBps": [],
"BlkioDeviceWriteBps": [],
"BlkioDeviceReadIOps": [],
"BlkioDeviceWriteIOps": [],
"CpuPeriod": 0,
"CpuQuota": 0,
"CpuRealtimePeriod": 0,
"CpuRealtimeRuntime": 0,
"CpusetCpus": "",
"CpusetMems": "",
"Devices": [],
"DeviceCgroupRules": null,
"DeviceRequests": null,
"MemoryReservation": 0,
"MemorySwap": 0,
"MemorySwappiness": null,
"OomKillDisable": null,
"PidsLimit": null,
"Ulimits": [
{
"Name": "core",
"Hard": -1,
"Soft": -1
}
],
"CpuCount": 0,
"CpuPercent": 0,
"IOMaximumIOps": 0,
"IOMaximumBandwidth": 0,
"MaskedPaths": null,
"ReadonlyPaths": null
},
"Storage": {
"RootFS": {
"Snapshot": {
"Name": "overlayfs"
}
}
},
"Mounts": [
{
"Type": "bind",
"Source": "/data2/GLM-5.2-w4a8",
"Destination": "/models",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
"Destination": "/workspace/ShareGPT_V3_unfiltered_cleaned_split.json",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke",
"Destination": "/workspace/run",
"Mode": "",
"RW": true,
"Propagation": "rprivate"
}
],
"Config": {
"Hostname": "gpu051",
"Domainname": "",
"User": "",
"AttachStdin": false,
"AttachStdout": false,
"AttachStderr": false,
"Tty": false,
"OpenStdin": false,
"StdinOnce": false,
"Env": [
"CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"XPU_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"CUDA_DISABLE_PRINTF=1",
"GLOO_SOCKET_TIMEOUT=60000",
"PATH=/root/miniconda/envs/python310_torch25_cuda/lib/python3.10/site-packages/torch_xmlir/xre/bin/:/root/miniconda/bin:/root/.cargo/bin:/usr/local/go/bin:/usr/local/cuda-11.7/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
"TZ=Asia/Shanghai",
"LANG=zh_CN.UTF-8"
],
"Cmd": [
"bash",
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"Image": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"Volumes": null,
"WorkingDir": "/workspace/run",
"Entrypoint": null,
"Labels": {
"autofix_time": "2025-12-03T10:19:26",
"description": "infer_ubuntu2204_dev runtime + miniconda",
"maintainer": "wenli <wenli01@baidu.com>",
"org.opencontainers.image.ref.name": "ubuntu",
"org.opencontainers.image.version": "22.04",
"version": "infer_ubuntu2204_dev:miniconda_0.1"
}
},
"NetworkSettings": {
"SandboxID": "81c79e65bbac2dcf756cbff44c4a0ba01bd8be20cc29b1b7907701dfb0a30619",
"SandboxKey": "/var/run/docker/netns/default",
"Ports": {},
"Networks": {
"host": {
"IPAMConfig": null,
"Links": null,
"Aliases": null,
"DriverOpts": null,
"GwPriority": 0,
"NetworkID": "0e3fdd7bc7639e6dc911f6f09344de480a35fa47ce2e83ff21a8160e319f48ac",
"EndpointID": "35fe2742654dbbedd58999151fd8a77234c95ea9204ebd61074cd27d27d85871",
"Gateway": "",
"IPAddress": "",
"MacAddress": "",
"IPPrefixLen": 0,
"IPv6Gateway": "",
"GlobalIPv6Address": "",
"GlobalIPv6PrefixLen": 0,
"DNSNames": null
}
}
},
"ImageManifestDescriptor": {
"mediaType": "application/vnd.oci.image.manifest.v1+json",
"digest": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"size": 3632,
"annotations": {
"io.containerd.image.name": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"org.opencontainers.image.ref.name": "20260715_5746"
},
"platform": {
"architecture": "amd64",
"os": "linux"
}
}
}
]

111
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-sharegpt-c1-c32-sweep/xpu_after_sweep.txt Normal file
View File

@ -0,0 +1,111 @@
Mon Aug 17 16:11:51 2026
+-----------------------------------------------------------------------------+
| XPU-SMI Driver Version: 5.19.0.0 XPU-RT Version: 5.19.0 |
|-------------------------------+----------------------+----------------------+
| XPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | XPU-Util Compute M. |
| | L3-Usage | SR-IOV M. |
|===============================+======================+======================|
| 0 P800 OAM N/A | 00000000:03:00.0 N/A | 0 |
| N/A 41C N/A 89W / 400W | 87970MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 1 P800 OAM N/A | 00000000:05:00.0 N/A | 0 |
| N/A 47C N/A 90W / 400W | 87970MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 2 P800 OAM N/A | 00000000:63:00.0 N/A | 0 |
| N/A 40C N/A 90W / 400W | 87970MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 3 P800 OAM N/A | 00000000:65:00.0 N/A | 0 |
| N/A 48C N/A 91W / 400W | 87968MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 4 P800 OAM N/A | 00000000:83:00.0 N/A | 0 |
| N/A 41C N/A 86W / 400W | 88318MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 5 P800 OAM N/A | 00000000:85:00.0 N/A | 0 |
| N/A 48C N/A 88W / 400W | 87970MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 6 P800 OAM N/A | 00000000:A3:00.0 N/A | 0 |
| N/A 43C N/A 88W / 400W | 87922MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 7 P800 OAM N/A | 00000000:A5:00.0 N/A | 0 |
| N/A 51C N/A 90W / 400W | 88306MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| XPU XI CI PID Type Process name XPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 0 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 0 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 0 N/A N/A 137943 C sglang::scheduler_TP3_EP3 87838MiB |
| 0 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 0 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 0 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 0 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 1 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 1 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 1 N/A N/A 137942 C sglang::scheduler_TP2_EP2 87838MiB |
| 1 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 1 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 1 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 1 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 1 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 2 N/A N/A 137940 C sglang::scheduler_TP0_EP0 87838MiB |
| 2 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 2 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 2 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 2 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 2 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 2 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 2 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 3 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 3 N/A N/A 137941 C sglang::scheduler_TP1_EP1 87836MiB |
| 3 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 3 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 3 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 3 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 3 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 3 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 4 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 4 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 4 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 4 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 4 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 4 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 4 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 4 N/A N/A 137947 C sglang::scheduler_TP7_EP7 88186MiB |
| 5 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 5 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 5 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 5 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 5 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 5 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 5 N/A N/A 137946 C sglang::scheduler_TP6_EP6 87838MiB |
| 5 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 6 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 6 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 6 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 6 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 6 N/A N/A 137944 C sglang::scheduler_TP4_EP4 87790MiB |
| 6 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 6 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 6 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 7 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 7 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 7 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 7 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 7 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 7 N/A N/A 137945 C sglang::scheduler_TP5_EP5 88174MiB |
| 7 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 7 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
+-----------------------------------------------------------------------------+

111
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260817-sharegpt-c1-c32-sweep/xpu_before_sweep.txt Normal file
View File

@ -0,0 +1,111 @@
Mon Aug 17 16:00:14 2026
+-----------------------------------------------------------------------------+
| XPU-SMI Driver Version: 5.19.0.0 XPU-RT Version: 5.19.0 |
|-------------------------------+----------------------+----------------------+
| XPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | XPU-Util Compute M. |
| | L3-Usage | SR-IOV M. |
|===============================+======================+======================|
| 0 P800 OAM N/A | 00000000:03:00.0 N/A | 0 |
| N/A 39C N/A 89W / 400W | 87958MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 1 P800 OAM N/A | 00000000:05:00.0 N/A | 0 |
| N/A 43C N/A 94W / 400W | 87958MiB / 98304MiB | 0% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 2 P800 OAM N/A | 00000000:63:00.0 N/A | 0 |
| N/A 38C N/A 95W / 400W | 87958MiB / 98304MiB | 33% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 3 P800 OAM N/A | 00000000:65:00.0 N/A | 0 |
| N/A 44C N/A 92W / 400W | 87958MiB / 98304MiB | 32% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 4 P800 OAM N/A | 00000000:83:00.0 N/A | 0 |
| N/A 39C N/A 90W / 400W | 88310MiB / 98304MiB | 29% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 5 P800 OAM N/A | 00000000:85:00.0 N/A | 0 |
| N/A 44C N/A 95W / 400W | 87958MiB / 98304MiB | 29% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 6 P800 OAM N/A | 00000000:A3:00.0 N/A | 0 |
| N/A 41C N/A 92W / 400W | 87914MiB / 98304MiB | 30% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
| 7 P800 OAM N/A | 00000000:A5:00.0 N/A | 0 |
| N/A 48C N/A 89W / 400W | 88292MiB / 98304MiB | 3% Default |
| | 92MiB / 96MiB | Disabled |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| XPU XI CI PID Type Process name XPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 0 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 0 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 0 N/A N/A 137943 C sglang::scheduler_TP3_EP3 87826MiB |
| 0 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 0 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 0 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 0 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 1 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 1 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 1 N/A N/A 137942 C sglang::scheduler_TP2_EP2 87826MiB |
| 1 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 1 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 1 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 1 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 1 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 2 N/A N/A 137940 C sglang::scheduler_TP0_EP0 87826MiB |
| 2 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 2 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 2 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 2 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 2 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 2 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 2 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 3 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 3 N/A N/A 137941 C sglang::scheduler_TP1_EP1 87826MiB |
| 3 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 3 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 3 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 3 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 3 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 3 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 4 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 4 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 4 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 4 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 4 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 4 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 4 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 4 N/A N/A 137947 C sglang::scheduler_TP7_EP7 88178MiB |
| 5 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 5 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 5 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 5 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 5 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 5 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 5 N/A N/A 137946 C sglang::scheduler_TP6_EP6 87826MiB |
| 5 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 6 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 6 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 6 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 6 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 6 N/A N/A 137944 C sglang::scheduler_TP4_EP4 87782MiB |
| 6 N/A N/A 137945 C sglang::scheduler_TP5_EP5 32MiB |
| 6 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 6 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
| 7 N/A N/A 137940 C sglang::scheduler_TP0_EP0 32MiB |
| 7 N/A N/A 137941 C sglang::scheduler_TP1_EP1 32MiB |
| 7 N/A N/A 137942 C sglang::scheduler_TP2_EP2 32MiB |
| 7 N/A N/A 137943 C sglang::scheduler_TP3_EP3 32MiB |
| 7 N/A N/A 137944 C sglang::scheduler_TP4_EP4 32MiB |
| 7 N/A N/A 137945 C sglang::scheduler_TP5_EP5 88160MiB |
| 7 N/A N/A 137946 C sglang::scheduler_TP6_EP6 32MiB |
| 7 N/A N/A 137947 C sglang::scheduler_TP7_EP7 32MiB |
+-----------------------------------------------------------------------------+

231
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/container_inspect.json Normal file
View File

@ -0,0 +1,231 @@
[
{
"Id": "5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180",
"Created": "2026-08-17T15:52:21.087868771Z",
"Path": "bash",
"Args": [
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"State": {
"Status": "running",
"Running": true,
"Paused": false,
"Restarting": false,
"OOMKilled": false,
"Dead": false,
"Pid": 137722,
"ExitCode": 0,
"Error": "",
"StartedAt": "2026-08-17T15:52:21.126324465Z",
"FinishedAt": "0001-01-01T00:00:00Z"
},
"Image": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"ResolvConfPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/resolv.conf",
"HostnamePath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/hostname",
"HostsPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/hosts",
"LogPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180-json.log",
"Name": "/glm52-w4a8-tp8",
"RestartCount": 0,
"Driver": "overlayfs",
"Platform": "linux",
"MountLabel": "",
"ProcessLabel": "",
"AppArmorProfile": "unconfined",
"ExecIDs": null,
"HostConfig": {
"Binds": [
"/data2/GLM-5.2-w4a8:/models:ro",
"/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json:/workspace/ShareGPT_V3_unfiltered_cleaned_split.json:ro",
"/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke:/workspace/run"
],
"ContainerIDFile": "",
"LogConfig": {
"Type": "json-file",
"Config": {}
},
"NetworkMode": "host",
"PortBindings": {},
"RestartPolicy": {
"Name": "no",
"MaximumRetryCount": 0
},
"AutoRemove": false,
"VolumeDriver": "",
"VolumesFrom": null,
"ConsoleSize": [
0,
0
],
"CapAdd": null,
"CapDrop": null,
"CgroupnsMode": "private",
"Dns": null,
"DnsOptions": [],
"DnsSearch": [],
"ExtraHosts": null,
"GroupAdd": null,
"IpcMode": "host",
"Cgroup": "",
"Links": null,
"OomScoreAdj": 0,
"PidMode": "",
"Privileged": true,
"PublishAllPorts": false,
"ReadonlyRootfs": false,
"SecurityOpt": [
"seccomp=unconfined",
"label=disable"
],
"UTSMode": "host",
"UsernsMode": "",
"ShmSize": 274877906944,
"Runtime": "runc",
"Isolation": "",
"CpuShares": 0,
"Memory": 0,
"NanoCpus": 0,
"CgroupParent": "",
"BlkioWeight": 0,
"BlkioWeightDevice": [],
"BlkioDeviceReadBps": [],
"BlkioDeviceWriteBps": [],
"BlkioDeviceReadIOps": [],
"BlkioDeviceWriteIOps": [],
"CpuPeriod": 0,
"CpuQuota": 0,
"CpuRealtimePeriod": 0,
"CpuRealtimeRuntime": 0,
"CpusetCpus": "",
"CpusetMems": "",
"Devices": [],
"DeviceCgroupRules": null,
"DeviceRequests": null,
"MemoryReservation": 0,
"MemorySwap": 0,
"MemorySwappiness": null,
"OomKillDisable": null,
"PidsLimit": null,
"Ulimits": [
{
"Name": "core",
"Hard": -1,
"Soft": -1
}
],
"CpuCount": 0,
"CpuPercent": 0,
"IOMaximumIOps": 0,
"IOMaximumBandwidth": 0,
"MaskedPaths": null,
"ReadonlyPaths": null
},
"Storage": {
"RootFS": {
"Snapshot": {
"Name": "overlayfs"
}
}
},
"Mounts": [
{
"Type": "bind",
"Source": "/data2/GLM-5.2-w4a8",
"Destination": "/models",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
"Destination": "/workspace/ShareGPT_V3_unfiltered_cleaned_split.json",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke",
"Destination": "/workspace/run",
"Mode": "",
"RW": true,
"Propagation": "rprivate"
}
],
"Config": {
"Hostname": "gpu051",
"Domainname": "",
"User": "",
"AttachStdin": false,
"AttachStdout": false,
"AttachStderr": false,
"Tty": false,
"OpenStdin": false,
"StdinOnce": false,
"Env": [
"CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"XPU_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"CUDA_DISABLE_PRINTF=1",
"GLOO_SOCKET_TIMEOUT=60000",
"PATH=/root/miniconda/envs/python310_torch25_cuda/lib/python3.10/site-packages/torch_xmlir/xre/bin/:/root/miniconda/bin:/root/.cargo/bin:/usr/local/go/bin:/usr/local/cuda-11.7/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
"TZ=Asia/Shanghai",
"LANG=zh_CN.UTF-8"
],
"Cmd": [
"bash",
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"Image": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"Volumes": null,
"WorkingDir": "/workspace/run",
"Entrypoint": null,
"Labels": {
"autofix_time": "2025-12-03T10:19:26",
"description": "infer_ubuntu2204_dev runtime + miniconda",
"maintainer": "wenli <wenli01@baidu.com>",
"org.opencontainers.image.ref.name": "ubuntu",
"org.opencontainers.image.version": "22.04",
"version": "infer_ubuntu2204_dev:miniconda_0.1"
}
},
"NetworkSettings": {
"SandboxID": "81c79e65bbac2dcf756cbff44c4a0ba01bd8be20cc29b1b7907701dfb0a30619",
"SandboxKey": "/var/run/docker/netns/default",
"Ports": {},
"Networks": {
"host": {
"IPAMConfig": null,
"Links": null,
"Aliases": null,
"DriverOpts": null,
"GwPriority": 0,
"NetworkID": "0e3fdd7bc7639e6dc911f6f09344de480a35fa47ce2e83ff21a8160e319f48ac",
"EndpointID": "35fe2742654dbbedd58999151fd8a77234c95ea9204ebd61074cd27d27d85871",
"Gateway": "",
"IPAddress": "",
"MacAddress": "",
"IPPrefixLen": 0,
"IPv6Gateway": "",
"GlobalIPv6Address": "",
"GlobalIPv6PrefixLen": 0,
"DNSNames": null
}
}
},
"ImageManifestDescriptor": {
"mediaType": "application/vnd.oci.image.manifest.v1+json",
"digest": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"size": 3632,
"annotations": {
"io.containerd.image.name": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"org.opencontainers.image.ref.name": "20260715_5746"
},
"platform": {
"architecture": "amd64",
"os": "linux"
}
}
}
]

231
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/container_inspect.resume.20260818-020923.json Normal file
View File

@ -0,0 +1,231 @@
[
{
"Id": "5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180",
"Created": "2026-08-17T15:52:21.087868771Z",
"Path": "bash",
"Args": [
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"State": {
"Status": "running",
"Running": true,
"Paused": false,
"Restarting": false,
"OOMKilled": false,
"Dead": false,
"Pid": 194559,
"ExitCode": 0,
"Error": "",
"StartedAt": "2026-08-18T02:07:51.684912653Z",
"FinishedAt": "2026-08-18T01:49:40.51417112Z"
},
"Image": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"ResolvConfPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/resolv.conf",
"HostnamePath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/hostname",
"HostsPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/hosts",
"LogPath": "/data1/sora/evalscope/docker/images/containers/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180/5526e1da90d6b5fbd4304d4e407b198cf1a6b2ad76af31ee4b76077d35ece180-json.log",
"Name": "/glm52-w4a8-tp8",
"RestartCount": 0,
"Driver": "overlayfs",
"Platform": "linux",
"MountLabel": "",
"ProcessLabel": "",
"AppArmorProfile": "unconfined",
"ExecIDs": null,
"HostConfig": {
"Binds": [
"/data2/GLM-5.2-w4a8:/models:ro",
"/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json:/workspace/ShareGPT_V3_unfiltered_cleaned_split.json:ro",
"/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke:/workspace/run"
],
"ContainerIDFile": "",
"LogConfig": {
"Type": "json-file",
"Config": {}
},
"NetworkMode": "host",
"PortBindings": {},
"RestartPolicy": {
"Name": "no",
"MaximumRetryCount": 0
},
"AutoRemove": false,
"VolumeDriver": "",
"VolumesFrom": null,
"ConsoleSize": [
0,
0
],
"CapAdd": null,
"CapDrop": null,
"CgroupnsMode": "private",
"Dns": null,
"DnsOptions": [],
"DnsSearch": [],
"ExtraHosts": null,
"GroupAdd": null,
"IpcMode": "host",
"Cgroup": "",
"Links": null,
"OomScoreAdj": 0,
"PidMode": "",
"Privileged": true,
"PublishAllPorts": false,
"ReadonlyRootfs": false,
"SecurityOpt": [
"seccomp=unconfined",
"label=disable"
],
"UTSMode": "host",
"UsernsMode": "",
"ShmSize": 274877906944,
"Runtime": "runc",
"Isolation": "",
"CpuShares": 0,
"Memory": 0,
"NanoCpus": 0,
"CgroupParent": "",
"BlkioWeight": 0,
"BlkioWeightDevice": [],
"BlkioDeviceReadBps": [],
"BlkioDeviceWriteBps": [],
"BlkioDeviceReadIOps": [],
"BlkioDeviceWriteIOps": [],
"CpuPeriod": 0,
"CpuQuota": 0,
"CpuRealtimePeriod": 0,
"CpuRealtimeRuntime": 0,
"CpusetCpus": "",
"CpusetMems": "",
"Devices": [],
"DeviceCgroupRules": null,
"DeviceRequests": null,
"MemoryReservation": 0,
"MemorySwap": 0,
"MemorySwappiness": null,
"OomKillDisable": null,
"PidsLimit": null,
"Ulimits": [
{
"Name": "core",
"Hard": -1,
"Soft": -1
}
],
"CpuCount": 0,
"CpuPercent": 0,
"IOMaximumIOps": 0,
"IOMaximumBandwidth": 0,
"MaskedPaths": null,
"ReadonlyPaths": null
},
"Storage": {
"RootFS": {
"Snapshot": {
"Name": "overlayfs"
}
}
},
"Mounts": [
{
"Type": "bind",
"Source": "/data2/GLM-5.2-w4a8",
"Destination": "/models",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
"Destination": "/workspace/ShareGPT_V3_unfiltered_cleaned_split.json",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke",
"Destination": "/workspace/run",
"Mode": "",
"RW": true,
"Propagation": "rprivate"
}
],
"Config": {
"Hostname": "gpu051",
"Domainname": "",
"User": "",
"AttachStdin": false,
"AttachStdout": false,
"AttachStderr": false,
"Tty": false,
"OpenStdin": false,
"StdinOnce": false,
"Env": [
"CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"XPU_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"CUDA_DISABLE_PRINTF=1",
"GLOO_SOCKET_TIMEOUT=60000",
"PATH=/root/miniconda/envs/python310_torch25_cuda/lib/python3.10/site-packages/torch_xmlir/xre/bin/:/root/miniconda/bin:/root/.cargo/bin:/usr/local/go/bin:/usr/local/cuda-11.7/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
"TZ=Asia/Shanghai",
"LANG=zh_CN.UTF-8"
],
"Cmd": [
"bash",
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"Image": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"Volumes": null,
"WorkingDir": "/workspace/run",
"Entrypoint": null,
"Labels": {
"autofix_time": "2025-12-03T10:19:26",
"description": "infer_ubuntu2204_dev runtime + miniconda",
"maintainer": "wenli <wenli01@baidu.com>",
"org.opencontainers.image.ref.name": "ubuntu",
"org.opencontainers.image.version": "22.04",
"version": "infer_ubuntu2204_dev:miniconda_0.1"
}
},
"NetworkSettings": {
"SandboxID": "02aa573ca306f134cdbd46e5e4f7df8d14de30e27b9ef68bc83e41ef6db028c3",
"SandboxKey": "/var/run/docker/netns/default",
"Ports": {},
"Networks": {
"host": {
"IPAMConfig": null,
"Links": null,
"Aliases": null,
"DriverOpts": null,
"GwPriority": 0,
"NetworkID": "0e3fdd7bc7639e6dc911f6f09344de480a35fa47ce2e83ff21a8160e319f48ac",
"EndpointID": "9d8f2b98c63551f3a9576d7381f86190bf36916fceaee65c116c1cc1bd83053a",
"Gateway": "",
"IPAddress": "",
"MacAddress": "",
"IPPrefixLen": 0,
"IPv6Gateway": "",
"GlobalIPv6Address": "",
"GlobalIPv6PrefixLen": 0,
"DNSNames": null
}
}
},
"ImageManifestDescriptor": {
"mediaType": "application/vnd.oci.image.manifest.v1+json",
"digest": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"size": 3632,
"annotations": {
"io.containerd.image.name": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"org.opencontainers.image.ref.name": "20260715_5746"
},
"platform": {
"architecture": "amd64",
"os": "linux"
}
}
}
]

232
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/container_inspect.resume.20260818-035808.json Normal file
View File

@ -0,0 +1,232 @@
[
{
"Id": "ec1f7a67284e4e9815888959d86a56b7749357017d8a4b0f04b409d0a1120f87",
"Created": "2026-08-18T03:55:32.13494019Z",
"Path": "bash",
"Args": [
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"State": {
"Status": "running",
"Running": true,
"Paused": false,
"Restarting": false,
"OOMKilled": false,
"Dead": false,
"Pid": 256057,
"ExitCode": 0,
"Error": "",
"StartedAt": "2026-08-18T03:55:32.172163502Z",
"FinishedAt": "0001-01-01T00:00:00Z"
},
"Image": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"ResolvConfPath": "/data1/sora/evalscope/docker/images/containers/ec1f7a67284e4e9815888959d86a56b7749357017d8a4b0f04b409d0a1120f87/resolv.conf",
"HostnamePath": "/data1/sora/evalscope/docker/images/containers/ec1f7a67284e4e9815888959d86a56b7749357017d8a4b0f04b409d0a1120f87/hostname",
"HostsPath": "/data1/sora/evalscope/docker/images/containers/ec1f7a67284e4e9815888959d86a56b7749357017d8a4b0f04b409d0a1120f87/hosts",
"LogPath": "/data1/sora/evalscope/docker/images/containers/ec1f7a67284e4e9815888959d86a56b7749357017d8a4b0f04b409d0a1120f87/ec1f7a67284e4e9815888959d86a56b7749357017d8a4b0f04b409d0a1120f87-json.log",
"Name": "/glm52-w4a8-tp8",
"RestartCount": 0,
"Driver": "overlayfs",
"Platform": "linux",
"MountLabel": "",
"ProcessLabel": "",
"AppArmorProfile": "unconfined",
"ExecIDs": null,
"HostConfig": {
"Binds": [
"/data2/GLM-5.2-w4a8:/models:ro",
"/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json:/workspace/ShareGPT_V3_unfiltered_cleaned_split.json:ro",
"/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke:/workspace/run"
],
"ContainerIDFile": "",
"LogConfig": {
"Type": "json-file",
"Config": {}
},
"NetworkMode": "host",
"PortBindings": {},
"RestartPolicy": {
"Name": "no",
"MaximumRetryCount": 0
},
"AutoRemove": false,
"VolumeDriver": "",
"VolumesFrom": null,
"ConsoleSize": [
0,
0
],
"CapAdd": null,
"CapDrop": null,
"CgroupnsMode": "private",
"Dns": null,
"DnsOptions": [],
"DnsSearch": [],
"ExtraHosts": null,
"GroupAdd": null,
"IpcMode": "host",
"Cgroup": "",
"Links": null,
"OomScoreAdj": 0,
"PidMode": "",
"Privileged": true,
"PublishAllPorts": false,
"ReadonlyRootfs": false,
"SecurityOpt": [
"seccomp=unconfined",
"label=disable"
],
"UTSMode": "host",
"UsernsMode": "",
"ShmSize": 274877906944,
"Runtime": "runc",
"Isolation": "",
"CpuShares": 0,
"Memory": 0,
"NanoCpus": 0,
"CgroupParent": "",
"BlkioWeight": 0,
"BlkioWeightDevice": [],
"BlkioDeviceReadBps": [],
"BlkioDeviceWriteBps": [],
"BlkioDeviceReadIOps": [],
"BlkioDeviceWriteIOps": [],
"CpuPeriod": 0,
"CpuQuota": 0,
"CpuRealtimePeriod": 0,
"CpuRealtimeRuntime": 0,
"CpusetCpus": "",
"CpusetMems": "",
"Devices": [],
"DeviceCgroupRules": null,
"DeviceRequests": null,
"MemoryReservation": 0,
"MemorySwap": 0,
"MemorySwappiness": null,
"OomKillDisable": null,
"PidsLimit": null,
"Ulimits": [
{
"Name": "core",
"Hard": -1,
"Soft": -1
}
],
"CpuCount": 0,
"CpuPercent": 0,
"IOMaximumIOps": 0,
"IOMaximumBandwidth": 0,
"MaskedPaths": null,
"ReadonlyPaths": null,
"Init": true
},
"Storage": {
"RootFS": {
"Snapshot": {
"Name": "overlayfs"
}
}
},
"Mounts": [
{
"Type": "bind",
"Source": "/data2/GLM-5.2-w4a8",
"Destination": "/models",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
"Destination": "/workspace/ShareGPT_V3_unfiltered_cleaned_split.json",
"Mode": "ro",
"RW": false,
"Propagation": "rprivate"
},
{
"Type": "bind",
"Source": "/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke",
"Destination": "/workspace/run",
"Mode": "",
"RW": true,
"Propagation": "rprivate"
}
],
"Config": {
"Hostname": "gpu051",
"Domainname": "",
"User": "",
"AttachStdin": false,
"AttachStdout": false,
"AttachStderr": false,
"Tty": false,
"OpenStdin": false,
"StdinOnce": false,
"Env": [
"CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"XPU_VISIBLE_DEVICES=0,1,2,3,4,5,6,7",
"CUDA_DISABLE_PRINTF=1",
"GLOO_SOCKET_TIMEOUT=60000",
"PATH=/root/miniconda/envs/python310_torch25_cuda/lib/python3.10/site-packages/torch_xmlir/xre/bin/:/root/miniconda/bin:/root/.cargo/bin:/usr/local/go/bin:/usr/local/cuda-11.7/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
"TZ=Asia/Shanghai",
"LANG=zh_CN.UTF-8"
],
"Cmd": [
"bash",
"-lc",
"exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server --host 0.0.0.0 --port 30000 --model-path /models --served-model-name GLM-5.2-w4a8 --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --prefill-attention-backend klxdsa --decode-attention-backend klxdsa --trust-remote-code --disable-custom-all-reduce --disable-shared-experts-fusion --chunked-prefill-size 32768 --page-size 64 --mem-fraction-static 0.82 --max-prefill-tokens 32768 --max-running-requests 64 --tp-size 8 --ep-size 8 --quantization w4a8_int4 --kv-cache-dtype int8 --cuda-graph-max-bs 8 --disable-cuda-graph-padding --watchdog-timeout 3000000 --tool-call-parser glm47 --reasoning-parser glm45 --json-model-override-args '{\"index_topk_freq\": 4}' --allow-auto-truncate --enable-metrics"
],
"Image": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"Volumes": null,
"WorkingDir": "/workspace/run",
"Entrypoint": null,
"Labels": {
"autofix_time": "2025-12-03T10:19:26",
"description": "infer_ubuntu2204_dev runtime + miniconda",
"maintainer": "wenli <wenli01@baidu.com>",
"org.opencontainers.image.ref.name": "ubuntu",
"org.opencontainers.image.version": "22.04",
"version": "infer_ubuntu2204_dev:miniconda_0.1"
}
},
"NetworkSettings": {
"SandboxID": "40813e57fb14f319ce4dc5e1f06a130d63d9b1cd36916bc1ebc7c33eafe04cc2",
"SandboxKey": "/var/run/docker/netns/default",
"Ports": {},
"Networks": {
"host": {
"IPAMConfig": null,
"Links": null,
"Aliases": null,
"DriverOpts": null,
"GwPriority": 0,
"NetworkID": "0e3fdd7bc7639e6dc911f6f09344de480a35fa47ce2e83ff21a8160e319f48ac",
"EndpointID": "5eb7dfb7d5c85d6d8c88dc3595bfa83deff49cff1c3bcc1ab946a9b88b4bc3d4",
"Gateway": "",
"IPAddress": "",
"MacAddress": "",
"IPPrefixLen": 0,
"IPv6Gateway": "",
"GlobalIPv6Address": "",
"GlobalIPv6PrefixLen": 0,
"DNSNames": null
}
}
},
"ImageManifestDescriptor": {
"mediaType": "application/vnd.oci.image.manifest.v1+json",
"digest": "sha256:5079ea4ecbeff690457c801261cc4ef4f80cd29012b8bda5fd6742138b82069d",
"size": 3632,
"annotations": {
"io.containerd.image.name": "iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746",
"org.opencontainers.image.ref.name": "20260715_5746"
},
"platform": {
"architecture": "amd64",
"os": "linux"
}
}
}
]

17
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failure_boundaries.tsv Normal file
View File

@ -0,0 +1,17 @@
8192 2048 64 c64_i8192_o2048 kv_cache_decode_oom
8192 4096 64 c64_i8192_o4096 kv_cache_decode_oom
16384 512 32 c32_i16384_o512 xpu_kernel_launch_timeout
16384 2048 32 c32_i16384_o2048 out_of_memory
16384 4096 32 c32_i16384_o4096 kv_cache_decode_oom
32768 128 1 c1_i32768_o128 out_of_memory
65536 128 1 c1_i65536_o128 out_of_memory
65536 128 8 c8_i65536_o128 out_of_memory
65536 256 1 c1_i65536_o256 out_of_memory
65536 512 1 c1_i65536_o512 out_of_memory
65536 1024 1 c1_i65536_o1024 out_of_memory
65536 2048 1 c1_i65536_o2048 out_of_memory
131072 128 1 c1_i131072_o128 out_of_memory
131072 128 4 c4_i131072_o128 out_of_memory
131072 256 1 c1_i131072_o256 out_of_memory
131072 512 1 c1_i131072_o512 out_of_memory
131072 1024 1 c1_i131072_o1024 out_of_memory
1 8192 2048 64 c64_i8192_o2048 kv_cache_decode_oom
2 8192 4096 64 c64_i8192_o4096 kv_cache_decode_oom
3 16384 512 32 c32_i16384_o512 xpu_kernel_launch_timeout
4 16384 2048 32 c32_i16384_o2048 out_of_memory
5 16384 4096 32 c32_i16384_o4096 kv_cache_decode_oom
6 32768 128 1 c1_i32768_o128 out_of_memory
7 65536 128 1 c1_i65536_o128 out_of_memory
8 65536 128 8 c8_i65536_o128 out_of_memory
9 65536 256 1 c1_i65536_o256 out_of_memory
10 65536 512 1 c1_i65536_o512 out_of_memory
11 65536 1024 1 c1_i65536_o1024 out_of_memory
12 65536 2048 1 c1_i65536_o2048 out_of_memory
13 131072 128 1 c1_i131072_o128 out_of_memory
14 131072 128 4 c4_i131072_o128 out_of_memory
15 131072 256 1 c1_i131072_o256 out_of_memory
16 131072 512 1 c1_i131072_o512 out_of_memory
17 131072 1024 1 c1_i131072_o1024 out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i131072_o1024.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i131072_o128.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i131072_o256.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i131072_o512.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i32768_o128.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i65536_o1024.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i65536_o128.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i65536_o2048.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i65536_o256.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c1_i65536_o512.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c32_i16384_o2048.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c32_i16384_o4096.reason Normal file
View File

@ -0,0 +1 @@
kv_cache_decode_oom

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c32_i16384_o512.reason Normal file
View File

@ -0,0 +1 @@
previous_failure

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c4_i131072_o128.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c64_i8192_o2048.reason Normal file
View File

@ -0,0 +1 @@
kv_cache_decode_oom

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c64_i8192_o4096.reason Normal file
View File

@ -0,0 +1 @@
previous_failure

1
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/failures/c8_i65536_o128.reason Normal file
View File

@ -0,0 +1 @@
out_of_memory

93
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/matrix.json Normal file
View File

@ -0,0 +1,93 @@
{
"comment": "ISL/OSL matrix for dsv4_p800_sglang_tp_dp_matrix. Y=must test, P=optional (record skipped on failure), N=skip.",
"mode": "Y",
"notes": "P800 INT8 sustains at most ~131k input tokens, so ISL stops at 131072. Concurrency ranges match the H20 matrix; scenarios that exceed server capacity are recorded as failed/skipped and the run moves on.",
"matrix": {
"1024": {
"128": "Y",
"256": "Y",
"512": "Y",
"1024": "Y",
"2048": "Y",
"4096": "Y"
},
"4096": {
"128": "Y",
"256": "Y",
"512": "Y",
"1024": "Y",
"2048": "Y",
"4096": "Y"
},
"8192": {
"128": "Y",
"256": "Y",
"512": "Y",
"1024": "Y",
"2048": "Y",
"4096": "Y"
},
"16384": {
"128": "Y",
"256": "Y",
"512": "Y",
"1024": "Y",
"2048": "Y",
"4096": "P"
},
"32768": {
"128": "Y",
"256": "Y",
"512": "Y",
"1024": "Y",
"2048": "Y",
"4096": "P"
},
"65536": {
"128": "Y",
"256": "Y",
"512": "Y",
"1024": "Y",
"2048": "P",
"4096": "N"
},
"131072": {
"128": "Y",
"256": "Y",
"512": "Y",
"1024": "P",
"2048": "N",
"4096": "N"
}
},
"concurrency": {
"1024": {
"low": 1,
"high": 128
},
"4096": {
"low": 1,
"high": 64
},
"8192": {
"low": 1,
"high": 64
},
"16384": {
"low": 1,
"high": 32
},
"32768": {
"low": 1,
"high": 16
},
"65536": {
"low": 1,
"high": 8
},
"131072": {
"low": 1,
"high": 4
}
}
}

79
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/scenarios.tsv Normal file
View File

@ -0,0 +1,79 @@
mark input_len output_len concurrency num_prompts
Y 1024 128 1 5
Y 1024 128 128 640
Y 1024 256 1 5
Y 1024 256 128 640
Y 1024 512 1 5
Y 1024 512 128 640
Y 1024 1024 1 5
Y 1024 1024 128 640
Y 1024 2048 1 5
Y 1024 2048 128 640
Y 1024 4096 1 5
Y 1024 4096 128 640
Y 4096 128 1 5
Y 4096 128 64 320
Y 4096 256 1 5
Y 4096 256 64 320
Y 4096 512 1 5
Y 4096 512 64 320
Y 4096 1024 1 5
Y 4096 1024 64 320
Y 4096 2048 1 5
Y 4096 2048 64 320
Y 4096 4096 1 5
Y 4096 4096 64 320
Y 8192 128 1 5
Y 8192 128 64 320
Y 8192 256 1 5
Y 8192 256 64 320
Y 8192 512 1 5
Y 8192 512 64 320
Y 8192 1024 1 5
Y 8192 1024 64 320
Y 8192 2048 1 5
Y 8192 2048 64 320
Y 8192 4096 1 5
Y 8192 4096 64 320
Y 16384 128 1 5
Y 16384 128 32 160
Y 16384 256 1 5
Y 16384 256 32 160
Y 16384 512 1 5
Y 16384 512 32 160
Y 16384 1024 1 5
Y 16384 1024 32 160
Y 16384 2048 1 5
Y 16384 2048 32 160
P 16384 4096 1 5
P 16384 4096 32 160
Y 32768 128 1 5
Y 32768 128 16 80
Y 32768 256 1 5
Y 32768 256 16 80
Y 32768 512 1 5
Y 32768 512 16 80
Y 32768 1024 1 5
Y 32768 1024 16 80
Y 32768 2048 1 5
Y 32768 2048 16 80
P 32768 4096 1 5
P 32768 4096 16 80
Y 65536 128 1 5
Y 65536 128 8 40
Y 65536 256 1 5
Y 65536 256 8 40
Y 65536 512 1 5
Y 65536 512 8 40
Y 65536 1024 1 5
Y 65536 1024 8 40
P 65536 2048 1 5
P 65536 2048 8 40
Y 131072 128 1 5
Y 131072 128 4 20
Y 131072 256 1 5
Y 131072 256 4 20
Y 131072 512 1 5
Y 131072 512 4 20
P 131072 1024 1 5
P 131072 1024 4 20
1 mark input_len output_len concurrency num_prompts
2 Y 1024 128 1 5
3 Y 1024 128 128 640
4 Y 1024 256 1 5
5 Y 1024 256 128 640
6 Y 1024 512 1 5
7 Y 1024 512 128 640
8 Y 1024 1024 1 5
9 Y 1024 1024 128 640
10 Y 1024 2048 1 5
11 Y 1024 2048 128 640
12 Y 1024 4096 1 5
13 Y 1024 4096 128 640
14 Y 4096 128 1 5
15 Y 4096 128 64 320
16 Y 4096 256 1 5
17 Y 4096 256 64 320
18 Y 4096 512 1 5
19 Y 4096 512 64 320
20 Y 4096 1024 1 5
21 Y 4096 1024 64 320
22 Y 4096 2048 1 5
23 Y 4096 2048 64 320
24 Y 4096 4096 1 5
25 Y 4096 4096 64 320
26 Y 8192 128 1 5
27 Y 8192 128 64 320
28 Y 8192 256 1 5
29 Y 8192 256 64 320
30 Y 8192 512 1 5
31 Y 8192 512 64 320
32 Y 8192 1024 1 5
33 Y 8192 1024 64 320
34 Y 8192 2048 1 5
35 Y 8192 2048 64 320
36 Y 8192 4096 1 5
37 Y 8192 4096 64 320
38 Y 16384 128 1 5
39 Y 16384 128 32 160
40 Y 16384 256 1 5
41 Y 16384 256 32 160
42 Y 16384 512 1 5
43 Y 16384 512 32 160
44 Y 16384 1024 1 5
45 Y 16384 1024 32 160
46 Y 16384 2048 1 5
47 Y 16384 2048 32 160
48 P 16384 4096 1 5
49 P 16384 4096 32 160
50 Y 32768 128 1 5
51 Y 32768 128 16 80
52 Y 32768 256 1 5
53 Y 32768 256 16 80
54 Y 32768 512 1 5
55 Y 32768 512 16 80
56 Y 32768 1024 1 5
57 Y 32768 1024 16 80
58 Y 32768 2048 1 5
59 Y 32768 2048 16 80
60 P 32768 4096 1 5
61 P 32768 4096 16 80
62 Y 65536 128 1 5
63 Y 65536 128 8 40
64 Y 65536 256 1 5
65 Y 65536 256 8 40
66 Y 65536 512 1 5
67 Y 65536 512 8 40
68 Y 65536 1024 1 5
69 Y 65536 1024 8 40
70 P 65536 2048 1 5
71 P 65536 2048 8 40
72 Y 131072 128 1 5
73 Y 131072 128 4 20
74 Y 131072 256 1 5
75 Y 131072 256 4 20
76 Y 131072 512 1 5
77 Y 131072 512 4 20
78 P 131072 1024 1 5
79 P 131072 1024 4 20

79
experiments/p800/glm52_w4a8_sglang_tp8_single_node/results/20260818-glm52-w4a8-full-matrix/summary.tsv Normal file
View File

@ -0,0 +1,79 @@
mark input_len output_len concurrency num_prompts scenario status completed duration_s request_throughput input_throughput output_throughput total_token_throughput mean_ttft_ms p99_ttft_ms mean_tpot_ms p99_tpot_ms
Y 1024 128 1 5 c1_i1024_o128 "completed rc=0 duration_s=39" 5 17.02591361099985 0.2936699970549406 300.7180769842592 37.5897596230324 281.2652568012709 297.18383764105965 24.568037981093877 24.614217375115466
Y 1024 128 128 640 c128_i1024_o128 "completed rc=0 duration_s=365" 640 342.486345420999 1.8686876383736828 1913.5361416946512 239.1920177118314 41669.024385146906 45741.00833293076 183.7266033815086 187.1878648276444
Y 1024 256 1 5 c1_i1024_o256 "completed rc=0 duration_s=55" 5 32.81497869300074 0.1523694422226297 156.0263088359728 39.0065772089932 278.39411059903796 294.2181943576725 24.633620097259097 24.658055767057437
Y 1024 256 128 640 c128_i1024_o256 "completed rc=0 duration_s=597" 640 574.0754678120029 1.1148360030768392 1141.5920671506833 285.3980167876708 62527.62441754065 68956.42354271989 182.28569678729144 184.03258206838555
Y 1024 512 1 5 c1_i1024_o512 "completed rc=0 duration_s=87" 5 65.10708004299886 0.07679656339522269 78.63968091670803 39.319840458354015 279.30358499943395 294.0611118795641 24.93063542035209 24.953084254637705
Y 1024 512 128 640 c128_i1024_o512 "completed rc=0 duration_s=1065" 640 1042.2514380899993 0.6140552812983843 628.7926080495455 314.39630402477275 104649.0250889984 115665.911804529 182.58666003007582 184.05825803236687
Y 1024 1024 1 5 c1_i1024_o1024 "completed rc=0 duration_s=153" 5 131.8887679899999 0.03791073399350513 38.82059160934925 38.82059160934925 281.0054517998651 295.132770438795 25.5066858453576 25.511918811260603
Y 1024 1024 128 640 c128_i1024_o1024 "completed rc=0 duration_s=1983" 640 1956.396799541999 0.32713200111032015 334.98316913696783 334.98316913696783 186932.53216034532 207552.52155184935 180.55811861379217 181.34573211966844
Y 1024 2048 1 5 c1_i1024_o2048 "completed rc=0 duration_s=290" 5 268.2550993270015 0.01863897466457861 19.086310056528497 38.17262011305699 284.6344647994556 294.75402423980995 26.06863725754749 26.112281927875404
Y 1024 2048 128 640 c128_i1024_o2048 "completed rc=0 duration_s=3843" 640 3815.7466828769975 0.16772601883452407 171.75144328655264 343.5028865731053 354123.60505508434 393690.0640932885 181.0707906767069 181.93800417857398
Y 1024 4096 1 5 c1_i1024_o4096 "completed rc=0 duration_s=560" 5 537.174628175002 0.009307960089230216 9.531351131371741 38.125404525486964 287.3897543991916 295.1975400408264 26.164411530549657 26.182873973002035
Y 1024 4096 128 640 c128_i1024_o4096 "completed rc=0 duration_s=7630" 640 7595.250456256996 0.0842631857482416 86.2855022061994 345.1420088247976 694281.792547897 772382.6850643696 182.80351444481107 183.29835544574874
Y 4096 128 1 5 c1_i4096_o128 "completed rc=0 duration_s=49" 5 23.562466644005326 0.21220189191321703 869.178949276537 27.16184216489178 1348.1614620017353 1376.2398038062383 26.4617152897642 26.536813717162214
Y 4096 128 64 320 c64_i4096_o128 "completed rc=0 duration_s=539" 320 513.9221596100033 0.6226623896561228 2550.425148031479 79.70078587598371 52487.32021765952 81989.41991875166 395.8419637399347 719.1297852202871
Y 4096 256 1 5 c1_i4096_o256 "completed rc=0 duration_s=65" 5 40.363449060001585 0.12387444870153036 507.38974188146835 31.711858867591772 1348.8969976024237 1376.5715911236475 26.354579003910104 26.36532255057268
Y 4096 256 64 320 c64_i4096_o256 "completed rc=0 duration_s=650" 320 625.7480431649965 0.5113879356001801 2094.644984218338 130.91531151364612 51983.60868599389 80408.54887854264 286.82753786230273 448.62066245765556
Y 4096 512 1 5 c1_i4096_o512 "completed rc=0 duration_s=99" 5 73.99429440300446 0.0675727776086068 276.77809708485347 34.597262135606684 1350.9769304000656 1376.4231815637322 26.310007427002912 26.334555245552153
Y 4096 512 64 320 c64_i4096_o512 "completed rc=0 duration_s=880" 320 855.845617013998 0.37389920990243986 1531.4911637603936 191.4363954700492 51983.15175365303 80405.63672760378 233.1860918822221 314.11634894583517
Y 4096 1024 1 5 c1_i4096_o1024 "completed rc=0 duration_s=165" 5 141.22379078199447 0.03540479951935607 145.01805883128247 36.25451470782062 1351.8061094000586 1379.9816434006789 26.28578575601136 26.32495529572055
Y 4096 1024 64 320 c64_i4096_o1024 "completed rc=0 duration_s=1345" 320 1320.7957280260016 0.24227819125237235 992.3714713697171 248.09286784242929 51987.80489426904 80406.50598565124 207.37264829075608 247.74751702926565
Y 4096 2048 1 5 c1_i4096_o2048 "completed rc=0 duration_s=299" 5 276.0557316109989 0.01811228468549133 74.18791807177249 37.09395903588624 1359.5692171991686 1377.9620103552588 26.305917187592286 26.323675634277176
Y 4096 2048 64 320 c64_i4096_o2048 "completed rc=0 duration_s=2280" 320 2253.1854364559986 0.14202115583674427 581.7186543073045 290.85932715365226 51999.37922932156 80419.80255557828 194.7249239024334 215.13688206616618
Y 4096 4096 1 5 c1_i4096_o4096 "completed rc=0 duration_s=570" 5 546.1440214710019 0.009155094267136421 37.49926611819078 37.49926611819078 1356.901797800674 1381.4528299999074 26.341520792234874 26.363355306765136
Y 4096 4096 64 320 c64_i4096_o4096 "completed rc=0 duration_s=4137" 320 4106.892298439998 0.07791779689999466 319.1512961023781 319.1512961023781 52028.30068695314 80428.11315494073 187.86320509006177 197.8918995976436
Y 8192 128 1 5 c1_i8192_o128 "completed rc=0 duration_s=58" 5 31.345879535998392 0.1595105983310462 1306.7108215279304 20.417356586373913 2901.3523344008718 2943.8824014391867 26.498316146440686 26.53415173224786
Y 8192 128 64 320 c64_i8192_o128 "completed rc=0 duration_s=1027" 320 1001.4245687750008 0.3195447864749735 2617.7108908029827 40.901732668796605 102210.96021643761 179702.23191498037 772.015502173622 1472.9441806528812
Y 8192 256 1 5 c1_i8192_o256 "completed rc=0 duration_s=75" 5 48.29129336799815 0.10353833271554946 848.1860216057812 26.505813175180663 2907.958858400525 2941.109013320529 26.463175448623264 26.479798227135436
Y 8192 256 64 320 c64_i8192_o256 "completed rc=0 duration_s=1144" 320 1118.6142376200005 0.28606823446199137 2343.4709767126333 73.23346802226979 102227.62581890015 179676.9426185613 476.33626962411694 825.4012724687083
Y 8192 512 1 5 c1_i8192_o512 "completed rc=0 duration_s=110" 5 82.16094908700325 0.06085616166270568 498.53367634088494 31.15835477130531 2904.7368975981954 2941.0467594809597 26.467229087280366 26.505994761013312
Y 8192 512 64 320 c64_i8192_o512 "completed rc=0 duration_s=1380" 320 1352.1895057329966 0.23665321956964455 1938.6631747145282 121.16644841965801 102229.57628892828 179680.07008601096 329.1102014473765 503.40242396277046
Y 8192 1024 1 5 c1_i8192_o1024 "completed rc=0 duration_s=174" 5 150.05084697799612 0.03332203783383651 272.9741339347887 34.12176674184859 2906.111534401134 2942.81814436079 26.49209734721495 26.533382691103906
Y 8192 1024 64 320 c64_i8192_o1024 "completed rc=0 duration_s=1845" 320 1819.0112392769952 0.17591974864717758 1441.1345809176787 180.14182261470984 102239.29165678738 179664.01260017834 255.6465966483472 343.00634268297966
Y 8192 2048 1 5 c1_i8192_o2048 "completed rc=0 duration_s=310" 5 285.48406155599514 0.017514112601411534 143.47561043076328 35.86890260769082 2907.4056262004888 2944.1087911635987 26.47123923947269 26.497441076600033
Y 8192 2048 64 320 c64_i8192_o2048 "failed rc=1 duration_s=553" 0
Y 8192 4096 1 5 c1_i8192_o4096 "completed rc=0 duration_s=584" 5 558.9306328860039 0.008945653907324436 73.28279680880178 36.64139840440089 2908.0996894001146 2962.2204470040742 26.58702289313796 26.61703713931074
Y 8192 4096 64 320 c64_i8192_o4096 "failed rc=1 duration_s=719 reason=kv_cache_decode_oom" 0
Y 16384 128 1 5 c1_i16384_o128 "completed rc=0 duration_s=76" 5 47.921742649996304 0.10433677332058344 1709.4536940844391 13.35510698503468 6168.107185598637 6217.074746359431 26.87305271969036 26.958400565712882
Y 16384 128 32 160 c32_i16384_o128 "completed rc=0 duration_s=1104" 160 1080.5961769310015 0.1480664131668646 2425.92011332591 18.95250088535867 107607.05564736869 194812.25933963628 854.2913843793324 1609.9457858553585
Y 16384 256 1 5 c1_i16384_o256 "completed rc=0 duration_s=93" 5 65.06508007799857 0.07684613611488852 1259.0470941063336 19.672610845411462 6165.073253607261 6211.129082086845 26.841394899609302 26.881746652878494
Y 16384 256 32 160 c32_i16384_o256 "completed rc=0 duration_s=1214" 160 1191.412069234997 0.1342944260273741 2200.279876032497 34.37937306300777 107601.49405923122 194837.96724378655 512.4159163919377 888.8134474421043
Y 16384 512 1 5 c1_i16384_o512 "completed rc=0 duration_s=127" 5 99.36944190099894 0.05031727968223334 824.398310313711 25.76244719730347 6175.6319466017885 6251.701926806127 26.801992351080585 26.82276618959694
Y 16384 512 32 160 c32_i16384_o512 "failed rc=1 duration_s=560 reason=xpu_kernel_launch_timeout" 0
Y 16384 1024 1 5 c1_i16384_o1024 "completed rc=0 duration_s=224" 5 171.96120902399707 0.029076324994332027 476.38650870713593 29.774156794195996 6928.77221259987 9792.07814124471 26.842475365785894 26.88422662580788
Y 16384 1024 32 160 c32_i16384_o1024 "completed rc=0 duration_s=1882" 160 1853.834564181001 0.08630759350993428 1414.0636120667632 88.3789757541727 107601.72120737507 194817.03514240915 257.23059973136543 351.1609817709484
Y 16384 2048 1 5 c1_i16384_o2048 "completed rc=0 duration_s=334" 5 305.36463945500145 0.016373867023122695 268.26943730684224 33.53367966335528 6173.947739601135 6222.383297723136 26.817756513432563 26.837409417542258
Y 16384 2048 32 160 c32_i16384_o2048 "failed rc=137 duration_s=167 reason=out_of_memory" 0
P 16384 4096 1 5 c1_i16384_o4096 "completed rc=0 duration_s=608" 5 580.1729553189944 0.008618119741984299 141.19927385267076 35.29981846316769 6178.636959602591 6234.941079312703 26.82611517767935 26.86785587242856
P 16384 4096 32 160 c32_i16384_o4096 "failed rc=137 duration_s=903 reason=kv_cache_decode_oom" 0
Y 32768 128 1 5 c1_i32768_o128 "failed rc=137 duration_s=29 reason=out_of_memory" 0
Y 32768 128 16 80 c16_i32768_o128 "completed rc=0 duration_s=1225" 80 1168.7748753930064 0.06844774103575729 2242.895578259695 8.761310852576933 124317.03163680068 214679.87077928378 861.6436795331623 1645.4117601102328
Y 32768 256 1 5 c1_i32768_o256 "completed rc=0 duration_s=134" 5 100.38509806500224 0.0498081896255394 1632.114757649675 12.750896544138087 13168.107665798743 13302.10535181046 27.085759039219543 27.132425062000003
Y 32768 256 16 80 c16_i32768_o256 "completed rc=0 duration_s=1286" 80 1263.4621468810074 0.06331808214238047 2074.806915641523 16.2094290284494 122892.92924403744 210721.14786341554 508.9795435045581 891.4333398982063
Y 32768 512 1 5 c1_i32768_o512 "completed rc=0 duration_s=170" 5 135.05323958600638 0.03702243659853738 1213.1512024608728 18.955487538451138 13167.90345320187 13303.137884192984 27.085512908023635 27.110341254001163
Y 32768 512 16 80 c16_i32768_o512 "completed rc=0 duration_s=1505" 80 1482.1555456469941 0.053975441535104335 1768.6672682222988 27.63542606597342 122898.48796358638 210686.75379800465 339.5751358392154 530.3086735966258
Y 32768 1024 1 5 c1_i32768_o1024 "completed rc=0 duration_s=238" 5 204.34472282300703 0.024468456688899888 801.7823887818715 25.055699649433485 13170.243986597052 13308.293756752973 27.073815555036006 27.08208811331908
Y 32768 1024 16 80 c16_i32768_o1024 "completed rc=0 duration_s=1944" 80 1921.5543885630032 0.04163296156286601 1364.2288844919933 42.63215264037479 122883.37932371232 210621.58506435342 255.5393236051565 350.83823580940947
Y 32768 2048 1 5 c1_i32768_o2048 "completed rc=0 duration_s=377" 5 342.98018497200974 0.014578101648665345 477.695234823466 29.855952176466626 13179.81927599758 13319.727632589638 27.07057905745223 27.088217141381012
Y 32768 2048 16 80 c16_i32768_o2048 "completed rc=0 duration_s=2827" 80 2803.750278225998 0.02853321161348862 934.9762781507951 58.436017384424694 122899.37849756316 210673.82780143176 213.8925572432094 261.5382891697284
P 32768 4096 1 5 c1_i32768_o4096 "completed rc=0 duration_s=655" 5 620.6336467729998 0.008056282520288137 263.98826562480167 32.99853320310021 13185.259522197885 13320.523270551348 27.091213466128522 27.119225907115602
P 32768 4096 16 80 c16_i32768_o4096 "completed rc=0 duration_s=4598" 80 4574.679185062007 0.017487565086799776 573.032532764255 71.62906659553188 122919.97263983685 210664.48323895675 193.40684656185272 217.6030520283007
Y 65536 128 1 5 c1_i65536_o128 "failed rc=137 duration_s=33 reason=out_of_memory" 0
Y 65536 128 8 40 c8_i65536_o128 "failed rc=137 duration_s=29 reason=out_of_memory" 0
Y 65536 256 1 5 c1_i65536_o256 "failed rc=137 duration_s=54 reason=out_of_memory" 0
Y 65536 256 8 40 c8_i65536_o256 "skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128" 0
Y 65536 512 1 5 c1_i65536_o512 "failed rc=137 duration_s=33 reason=out_of_memory" 0
Y 65536 512 8 40 c8_i65536_o512 "skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128" 0
Y 65536 1024 1 5 c1_i65536_o1024 "failed rc=137 duration_s=34 reason=out_of_memory" 0
Y 65536 1024 8 40 c8_i65536_o1024 "skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128" 0
P 65536 2048 1 5 c1_i65536_o2048 "failed rc=137 duration_s=33 reason=out_of_memory" 0
P 65536 2048 8 40 c8_i65536_o2048 "skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128" 0
Y 131072 128 1 5 c1_i131072_o128 "failed rc=137 duration_s=34 reason=out_of_memory" 0
Y 131072 128 4 20 c4_i131072_o128 "failed rc=137 duration_s=34 reason=out_of_memory" 0
Y 131072 256 1 5 c1_i131072_o256 "failed rc=137 duration_s=33 reason=out_of_memory" 0
Y 131072 256 4 20 c4_i131072_o256 "skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128" 0
Y 131072 512 1 5 c1_i131072_o512 "failed rc=137 duration_s=33 reason=out_of_memory" 0
Y 131072 512 4 20 c4_i131072_o512 "skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128" 0
P 131072 1024 1 5 c1_i131072_o1024 "failed rc=1 duration_s=28 reason=out_of_memory" 0
P 131072 1024 4 20 c4_i131072_o1024 "skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128" 0
1 mark input_len output_len concurrency num_prompts scenario status completed duration_s request_throughput input_throughput output_throughput total_token_throughput mean_ttft_ms p99_ttft_ms mean_tpot_ms p99_tpot_ms
2 Y 1024 128 1 5 c1_i1024_o128 completed rc=0 duration_s=39 5 17.02591361099985 0.2936699970549406 300.7180769842592 37.5897596230324 281.2652568012709 297.18383764105965 24.568037981093877 24.614217375115466
3 Y 1024 128 128 640 c128_i1024_o128 completed rc=0 duration_s=365 640 342.486345420999 1.8686876383736828 1913.5361416946512 239.1920177118314 41669.024385146906 45741.00833293076 183.7266033815086 187.1878648276444
4 Y 1024 256 1 5 c1_i1024_o256 completed rc=0 duration_s=55 5 32.81497869300074 0.1523694422226297 156.0263088359728 39.0065772089932 278.39411059903796 294.2181943576725 24.633620097259097 24.658055767057437
5 Y 1024 256 128 640 c128_i1024_o256 completed rc=0 duration_s=597 640 574.0754678120029 1.1148360030768392 1141.5920671506833 285.3980167876708 62527.62441754065 68956.42354271989 182.28569678729144 184.03258206838555
6 Y 1024 512 1 5 c1_i1024_o512 completed rc=0 duration_s=87 5 65.10708004299886 0.07679656339522269 78.63968091670803 39.319840458354015 279.30358499943395 294.0611118795641 24.93063542035209 24.953084254637705
7 Y 1024 512 128 640 c128_i1024_o512 completed rc=0 duration_s=1065 640 1042.2514380899993 0.6140552812983843 628.7926080495455 314.39630402477275 104649.0250889984 115665.911804529 182.58666003007582 184.05825803236687
8 Y 1024 1024 1 5 c1_i1024_o1024 completed rc=0 duration_s=153 5 131.8887679899999 0.03791073399350513 38.82059160934925 38.82059160934925 281.0054517998651 295.132770438795 25.5066858453576 25.511918811260603
9 Y 1024 1024 128 640 c128_i1024_o1024 completed rc=0 duration_s=1983 640 1956.396799541999 0.32713200111032015 334.98316913696783 334.98316913696783 186932.53216034532 207552.52155184935 180.55811861379217 181.34573211966844
10 Y 1024 2048 1 5 c1_i1024_o2048 completed rc=0 duration_s=290 5 268.2550993270015 0.01863897466457861 19.086310056528497 38.17262011305699 284.6344647994556 294.75402423980995 26.06863725754749 26.112281927875404
11 Y 1024 2048 128 640 c128_i1024_o2048 completed rc=0 duration_s=3843 640 3815.7466828769975 0.16772601883452407 171.75144328655264 343.5028865731053 354123.60505508434 393690.0640932885 181.0707906767069 181.93800417857398
12 Y 1024 4096 1 5 c1_i1024_o4096 completed rc=0 duration_s=560 5 537.174628175002 0.009307960089230216 9.531351131371741 38.125404525486964 287.3897543991916 295.1975400408264 26.164411530549657 26.182873973002035
13 Y 1024 4096 128 640 c128_i1024_o4096 completed rc=0 duration_s=7630 640 7595.250456256996 0.0842631857482416 86.2855022061994 345.1420088247976 694281.792547897 772382.6850643696 182.80351444481107 183.29835544574874
14 Y 4096 128 1 5 c1_i4096_o128 completed rc=0 duration_s=49 5 23.562466644005326 0.21220189191321703 869.178949276537 27.16184216489178 1348.1614620017353 1376.2398038062383 26.4617152897642 26.536813717162214
15 Y 4096 128 64 320 c64_i4096_o128 completed rc=0 duration_s=539 320 513.9221596100033 0.6226623896561228 2550.425148031479 79.70078587598371 52487.32021765952 81989.41991875166 395.8419637399347 719.1297852202871
16 Y 4096 256 1 5 c1_i4096_o256 completed rc=0 duration_s=65 5 40.363449060001585 0.12387444870153036 507.38974188146835 31.711858867591772 1348.8969976024237 1376.5715911236475 26.354579003910104 26.36532255057268
17 Y 4096 256 64 320 c64_i4096_o256 completed rc=0 duration_s=650 320 625.7480431649965 0.5113879356001801 2094.644984218338 130.91531151364612 51983.60868599389 80408.54887854264 286.82753786230273 448.62066245765556
18 Y 4096 512 1 5 c1_i4096_o512 completed rc=0 duration_s=99 5 73.99429440300446 0.0675727776086068 276.77809708485347 34.597262135606684 1350.9769304000656 1376.4231815637322 26.310007427002912 26.334555245552153
19 Y 4096 512 64 320 c64_i4096_o512 completed rc=0 duration_s=880 320 855.845617013998 0.37389920990243986 1531.4911637603936 191.4363954700492 51983.15175365303 80405.63672760378 233.1860918822221 314.11634894583517
20 Y 4096 1024 1 5 c1_i4096_o1024 completed rc=0 duration_s=165 5 141.22379078199447 0.03540479951935607 145.01805883128247 36.25451470782062 1351.8061094000586 1379.9816434006789 26.28578575601136 26.32495529572055
21 Y 4096 1024 64 320 c64_i4096_o1024 completed rc=0 duration_s=1345 320 1320.7957280260016 0.24227819125237235 992.3714713697171 248.09286784242929 51987.80489426904 80406.50598565124 207.37264829075608 247.74751702926565
22 Y 4096 2048 1 5 c1_i4096_o2048 completed rc=0 duration_s=299 5 276.0557316109989 0.01811228468549133 74.18791807177249 37.09395903588624 1359.5692171991686 1377.9620103552588 26.305917187592286 26.323675634277176
23 Y 4096 2048 64 320 c64_i4096_o2048 completed rc=0 duration_s=2280 320 2253.1854364559986 0.14202115583674427 581.7186543073045 290.85932715365226 51999.37922932156 80419.80255557828 194.7249239024334 215.13688206616618
24 Y 4096 4096 1 5 c1_i4096_o4096 completed rc=0 duration_s=570 5 546.1440214710019 0.009155094267136421 37.49926611819078 37.49926611819078 1356.901797800674 1381.4528299999074 26.341520792234874 26.363355306765136
25 Y 4096 4096 64 320 c64_i4096_o4096 completed rc=0 duration_s=4137 320 4106.892298439998 0.07791779689999466 319.1512961023781 319.1512961023781 52028.30068695314 80428.11315494073 187.86320509006177 197.8918995976436
26 Y 8192 128 1 5 c1_i8192_o128 completed rc=0 duration_s=58 5 31.345879535998392 0.1595105983310462 1306.7108215279304 20.417356586373913 2901.3523344008718 2943.8824014391867 26.498316146440686 26.53415173224786
27 Y 8192 128 64 320 c64_i8192_o128 completed rc=0 duration_s=1027 320 1001.4245687750008 0.3195447864749735 2617.7108908029827 40.901732668796605 102210.96021643761 179702.23191498037 772.015502173622 1472.9441806528812
28 Y 8192 256 1 5 c1_i8192_o256 completed rc=0 duration_s=75 5 48.29129336799815 0.10353833271554946 848.1860216057812 26.505813175180663 2907.958858400525 2941.109013320529 26.463175448623264 26.479798227135436
29 Y 8192 256 64 320 c64_i8192_o256 completed rc=0 duration_s=1144 320 1118.6142376200005 0.28606823446199137 2343.4709767126333 73.23346802226979 102227.62581890015 179676.9426185613 476.33626962411694 825.4012724687083
30 Y 8192 512 1 5 c1_i8192_o512 completed rc=0 duration_s=110 5 82.16094908700325 0.06085616166270568 498.53367634088494 31.15835477130531 2904.7368975981954 2941.0467594809597 26.467229087280366 26.505994761013312
31 Y 8192 512 64 320 c64_i8192_o512 completed rc=0 duration_s=1380 320 1352.1895057329966 0.23665321956964455 1938.6631747145282 121.16644841965801 102229.57628892828 179680.07008601096 329.1102014473765 503.40242396277046
32 Y 8192 1024 1 5 c1_i8192_o1024 completed rc=0 duration_s=174 5 150.05084697799612 0.03332203783383651 272.9741339347887 34.12176674184859 2906.111534401134 2942.81814436079 26.49209734721495 26.533382691103906
33 Y 8192 1024 64 320 c64_i8192_o1024 completed rc=0 duration_s=1845 320 1819.0112392769952 0.17591974864717758 1441.1345809176787 180.14182261470984 102239.29165678738 179664.01260017834 255.6465966483472 343.00634268297966
34 Y 8192 2048 1 5 c1_i8192_o2048 completed rc=0 duration_s=310 5 285.48406155599514 0.017514112601411534 143.47561043076328 35.86890260769082 2907.4056262004888 2944.1087911635987 26.47123923947269 26.497441076600033
35 Y 8192 2048 64 320 c64_i8192_o2048 failed rc=1 duration_s=553 0
36 Y 8192 4096 1 5 c1_i8192_o4096 completed rc=0 duration_s=584 5 558.9306328860039 0.008945653907324436 73.28279680880178 36.64139840440089 2908.0996894001146 2962.2204470040742 26.58702289313796 26.61703713931074
37 Y 8192 4096 64 320 c64_i8192_o4096 failed rc=1 duration_s=719 reason=kv_cache_decode_oom 0
38 Y 16384 128 1 5 c1_i16384_o128 completed rc=0 duration_s=76 5 47.921742649996304 0.10433677332058344 1709.4536940844391 13.35510698503468 6168.107185598637 6217.074746359431 26.87305271969036 26.958400565712882
39 Y 16384 128 32 160 c32_i16384_o128 completed rc=0 duration_s=1104 160 1080.5961769310015 0.1480664131668646 2425.92011332591 18.95250088535867 107607.05564736869 194812.25933963628 854.2913843793324 1609.9457858553585
40 Y 16384 256 1 5 c1_i16384_o256 completed rc=0 duration_s=93 5 65.06508007799857 0.07684613611488852 1259.0470941063336 19.672610845411462 6165.073253607261 6211.129082086845 26.841394899609302 26.881746652878494
41 Y 16384 256 32 160 c32_i16384_o256 completed rc=0 duration_s=1214 160 1191.412069234997 0.1342944260273741 2200.279876032497 34.37937306300777 107601.49405923122 194837.96724378655 512.4159163919377 888.8134474421043
42 Y 16384 512 1 5 c1_i16384_o512 completed rc=0 duration_s=127 5 99.36944190099894 0.05031727968223334 824.398310313711 25.76244719730347 6175.6319466017885 6251.701926806127 26.801992351080585 26.82276618959694
43 Y 16384 512 32 160 c32_i16384_o512 failed rc=1 duration_s=560 reason=xpu_kernel_launch_timeout 0
44 Y 16384 1024 1 5 c1_i16384_o1024 completed rc=0 duration_s=224 5 171.96120902399707 0.029076324994332027 476.38650870713593 29.774156794195996 6928.77221259987 9792.07814124471 26.842475365785894 26.88422662580788
45 Y 16384 1024 32 160 c32_i16384_o1024 completed rc=0 duration_s=1882 160 1853.834564181001 0.08630759350993428 1414.0636120667632 88.3789757541727 107601.72120737507 194817.03514240915 257.23059973136543 351.1609817709484
46 Y 16384 2048 1 5 c1_i16384_o2048 completed rc=0 duration_s=334 5 305.36463945500145 0.016373867023122695 268.26943730684224 33.53367966335528 6173.947739601135 6222.383297723136 26.817756513432563 26.837409417542258
47 Y 16384 2048 32 160 c32_i16384_o2048 failed rc=137 duration_s=167 reason=out_of_memory 0
48 P 16384 4096 1 5 c1_i16384_o4096 completed rc=0 duration_s=608 5 580.1729553189944 0.008618119741984299 141.19927385267076 35.29981846316769 6178.636959602591 6234.941079312703 26.82611517767935 26.86785587242856
49 P 16384 4096 32 160 c32_i16384_o4096 failed rc=137 duration_s=903 reason=kv_cache_decode_oom 0
50 Y 32768 128 1 5 c1_i32768_o128 failed rc=137 duration_s=29 reason=out_of_memory 0
51 Y 32768 128 16 80 c16_i32768_o128 completed rc=0 duration_s=1225 80 1168.7748753930064 0.06844774103575729 2242.895578259695 8.761310852576933 124317.03163680068 214679.87077928378 861.6436795331623 1645.4117601102328
52 Y 32768 256 1 5 c1_i32768_o256 completed rc=0 duration_s=134 5 100.38509806500224 0.0498081896255394 1632.114757649675 12.750896544138087 13168.107665798743 13302.10535181046 27.085759039219543 27.132425062000003
53 Y 32768 256 16 80 c16_i32768_o256 completed rc=0 duration_s=1286 80 1263.4621468810074 0.06331808214238047 2074.806915641523 16.2094290284494 122892.92924403744 210721.14786341554 508.9795435045581 891.4333398982063
54 Y 32768 512 1 5 c1_i32768_o512 completed rc=0 duration_s=170 5 135.05323958600638 0.03702243659853738 1213.1512024608728 18.955487538451138 13167.90345320187 13303.137884192984 27.085512908023635 27.110341254001163
55 Y 32768 512 16 80 c16_i32768_o512 completed rc=0 duration_s=1505 80 1482.1555456469941 0.053975441535104335 1768.6672682222988 27.63542606597342 122898.48796358638 210686.75379800465 339.5751358392154 530.3086735966258
56 Y 32768 1024 1 5 c1_i32768_o1024 completed rc=0 duration_s=238 5 204.34472282300703 0.024468456688899888 801.7823887818715 25.055699649433485 13170.243986597052 13308.293756752973 27.073815555036006 27.08208811331908
57 Y 32768 1024 16 80 c16_i32768_o1024 completed rc=0 duration_s=1944 80 1921.5543885630032 0.04163296156286601 1364.2288844919933 42.63215264037479 122883.37932371232 210621.58506435342 255.5393236051565 350.83823580940947
58 Y 32768 2048 1 5 c1_i32768_o2048 completed rc=0 duration_s=377 5 342.98018497200974 0.014578101648665345 477.695234823466 29.855952176466626 13179.81927599758 13319.727632589638 27.07057905745223 27.088217141381012
59 Y 32768 2048 16 80 c16_i32768_o2048 completed rc=0 duration_s=2827 80 2803.750278225998 0.02853321161348862 934.9762781507951 58.436017384424694 122899.37849756316 210673.82780143176 213.8925572432094 261.5382891697284
60 P 32768 4096 1 5 c1_i32768_o4096 completed rc=0 duration_s=655 5 620.6336467729998 0.008056282520288137 263.98826562480167 32.99853320310021 13185.259522197885 13320.523270551348 27.091213466128522 27.119225907115602
61 P 32768 4096 16 80 c16_i32768_o4096 completed rc=0 duration_s=4598 80 4574.679185062007 0.017487565086799776 573.032532764255 71.62906659553188 122919.97263983685 210664.48323895675 193.40684656185272 217.6030520283007
62 Y 65536 128 1 5 c1_i65536_o128 failed rc=137 duration_s=33 reason=out_of_memory 0
63 Y 65536 128 8 40 c8_i65536_o128 failed rc=137 duration_s=29 reason=out_of_memory 0
64 Y 65536 256 1 5 c1_i65536_o256 failed rc=137 duration_s=54 reason=out_of_memory 0
65 Y 65536 256 8 40 c8_i65536_o256 skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128 0
66 Y 65536 512 1 5 c1_i65536_o512 failed rc=137 duration_s=33 reason=out_of_memory 0
67 Y 65536 512 8 40 c8_i65536_o512 skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128 0
68 Y 65536 1024 1 5 c1_i65536_o1024 failed rc=137 duration_s=34 reason=out_of_memory 0
69 Y 65536 1024 8 40 c8_i65536_o1024 skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128 0
70 P 65536 2048 1 5 c1_i65536_o2048 failed rc=137 duration_s=33 reason=out_of_memory 0
71 P 65536 2048 8 40 c8_i65536_o2048 skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128 0
72 Y 131072 128 1 5 c1_i131072_o128 failed rc=137 duration_s=34 reason=out_of_memory 0
73 Y 131072 128 4 20 c4_i131072_o128 failed rc=137 duration_s=34 reason=out_of_memory 0
74 Y 131072 256 1 5 c1_i131072_o256 failed rc=137 duration_s=33 reason=out_of_memory 0
75 Y 131072 256 4 20 c4_i131072_o256 skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128 0
76 Y 131072 512 1 5 c1_i131072_o512 failed rc=137 duration_s=33 reason=out_of_memory 0
77 Y 131072 512 4 20 c4_i131072_o512 skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128 0
78 P 131072 1024 1 5 c1_i131072_o1024 failed rc=1 duration_s=28 reason=out_of_memory 0
79 P 131072 1024 4 20 c4_i131072_o1024 skipped reason=strictly_above_failed_boundary boundary=c1_i32768_o128 0

43
experiments/p800/glm52_w4a8_sglang_tp8_single_node/run_bench.sh Executable file
View File

@ -0,0 +1,43 @@
#!/usr/bin/env bash
set -Eeuo pipefail
CONTAINER="glm52-w4a8-tp8"
PORT="${PORT:-30000}"
RUN_DIR="/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke"
RUN_ID="${RUN_ID:-$(date '+%Y%m%d-%H%M%S')}"
RESULT_DIR="${RUN_DIR}/results/${RUN_ID}"
PYTHON="/root/miniconda/envs/python310_torch25_cuda/bin/python"
mkdir -p "${RESULT_DIR}"
curl --fail --silent --show-error --max-time 10 "http://127.0.0.1:${PORT}/health" >/dev/null
docker inspect "${CONTAINER}" >"${RESULT_DIR}/container_inspect.json"
docker logs "${CONTAINER}" >"${RESULT_DIR}/server_before_bench.log" 2>&1
xpu-smi >"${RESULT_DIR}/xpu_before_bench.txt"
docker exec "${CONTAINER}" env \
HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 HF_DATASETS_OFFLINE=1 \
"${PYTHON}" -m sglang.bench_serving \
--backend sglang \
--host 127.0.0.1 \
--port "${PORT}" \
--dataset-name sharegpt \
--dataset-path /workspace/ShareGPT_V3_unfiltered_cleaned_split.json \
--model /models \
--served-model-name GLM-5.2-w4a8 \
--tokenizer /models \
--num-prompts 64 \
--sharegpt-output-len 128 \
--sharegpt-context-len 32768 \
--request-rate inf \
--max-concurrency 8 \
--warmup-requests 2 \
--seed 1 \
--output-file "/workspace/run/results/${RUN_ID}/bench_sharegpt_c8_o128.jsonl" \
--output-details \
2>&1 | tee "${RESULT_DIR}/bench_console.log"
docker logs "${CONTAINER}" >"${RESULT_DIR}/server_after_bench.log" 2>&1
xpu-smi >"${RESULT_DIR}/xpu_after_bench.txt"
printf '%s\n' "${RESULT_DIR}"

46
experiments/p800/glm52_w4a8_sglang_tp8_single_node/run_concurrency_sweep.sh Executable file
View File

@ -0,0 +1,46 @@
#!/usr/bin/env bash
set -Eeuo pipefail
CONTAINER="glm52-w4a8-tp8"
PORT="${PORT:-30000}"
RUN_DIR="/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke"
RUN_ID="${RUN_ID:-$(date '+%Y%m%d-%H%M%S')-sharegpt-sweep}"
RESULT_DIR="${RUN_DIR}/results/${RUN_ID}"
PYTHON="/root/miniconda/envs/python310_torch25_cuda/bin/python"
CONCURRENCIES="${CONCURRENCIES:-1 2 4 8 16 32}"
NUM_PROMPTS="${NUM_PROMPTS:-64}"
OUTPUT_LEN="${OUTPUT_LEN:-128}"
mkdir -p "${RESULT_DIR}"
curl --fail --silent --show-error --max-time 10 "http://127.0.0.1:${PORT}/health" >/dev/null
docker inspect "${CONTAINER}" >"${RESULT_DIR}/container_inspect.json"
xpu-smi >"${RESULT_DIR}/xpu_before_sweep.txt"
for concurrency in ${CONCURRENCIES}; do
echo "===== concurrency=${concurrency} =====" | tee -a "${RESULT_DIR}/sweep.log"
docker exec "${CONTAINER}" env \
HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 HF_DATASETS_OFFLINE=1 \
"${PYTHON}" -m sglang.bench_serving \
--backend sglang \
--host 127.0.0.1 \
--port "${PORT}" \
--dataset-name sharegpt \
--dataset-path /workspace/ShareGPT_V3_unfiltered_cleaned_split.json \
--model /models \
--served-model-name GLM-5.2-w4a8 \
--tokenizer /models \
--num-prompts "${NUM_PROMPTS}" \
--sharegpt-output-len "${OUTPUT_LEN}" \
--sharegpt-context-len 32768 \
--request-rate inf \
--max-concurrency "${concurrency}" \
--warmup-requests 2 \
--seed 1 \
--output-file "/workspace/run/results/${RUN_ID}/bench_sharegpt_c${concurrency}_o${OUTPUT_LEN}.jsonl" \
--output-details \
2>&1 | tee "${RESULT_DIR}/bench_c${concurrency}.log" | tee -a "${RESULT_DIR}/sweep.log"
done
docker logs "${CONTAINER}" >"${RESULT_DIR}/server_after_sweep.log" 2>&1
xpu-smi >"${RESULT_DIR}/xpu_after_sweep.txt"
printf '%s\n' "${RESULT_DIR}"

234
experiments/p800/glm52_w4a8_sglang_tp8_single_node/run_full_matrix.sh Executable file
View File

@ -0,0 +1,234 @@
#!/usr/bin/env bash
set -Eeuo pipefail
CONTAINER="glm52-w4a8-tp8"
PORT="${PORT:-30000}"
RUN_DIR="/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke"
REFERENCE_DIR="/data1/wxy/sskj/experiments/p800/dsv4_p800_sglang_tp_dp_matrix"
RUN_ID="${RUN_ID:-$(date '+%Y%m%d-%H%M%S')-full-matrix}"
RESULT_DIR="${RUN_DIR}/results/${RUN_ID}"
RAW_DIR="${RESULT_DIR}/raw_outputs"
LOG_DIR="${RESULT_DIR}/logs"
PYTHON="/root/miniconda/envs/python310_torch25_cuda/bin/python"
SCENARIO_TIMEOUT_S="${SCENARIO_TIMEOUT_S:-28800}"
MATRIX_MODE="${MATRIX_MODE:-Y+P}"
SERVICE_RECOVERY_TIMEOUT_S="${SERVICE_RECOVERY_TIMEOUT_S:-900}"
FAILURE_DIR="${RESULT_DIR}/failures"
FAILURE_BOUNDARIES_FILE="${RESULT_DIR}/failure_boundaries.tsv"
mkdir -p "${RAW_DIR}" "${LOG_DIR}" "${FAILURE_DIR}"
exec > >(tee -a "${RESULT_DIR}/orchestrator.log") 2>&1
ensure_service() {
if curl --fail --silent --show-error --max-time 10 \
"http://127.0.0.1:${PORT}/health" >/dev/null 2>&1; then
return 0
fi
if [[ "$(docker inspect -f '{{.State.Running}}' "${CONTAINER}" 2>/dev/null || true)" == "true" ]]; then
echo "service_recovery=restart container=${CONTAINER}"
if ! docker restart "${CONTAINER}" >/dev/null; then
echo "service_recovery=recreate reason=restart_failed"
bash "${RUN_DIR}/start_glm52_w4a8.sh" >/dev/null
fi
else
echo "service_recovery=start container=${CONTAINER}"
if ! docker start "${CONTAINER}" >/dev/null; then
echo "service_recovery=recreate reason=start_failed"
bash "${RUN_DIR}/start_glm52_w4a8.sh" >/dev/null
fi
fi
local deadline=$(( $(date +%s) + SERVICE_RECOVERY_TIMEOUT_S ))
until curl --fail --silent --show-error --max-time 10 \
"http://127.0.0.1:${PORT}/health" >/dev/null 2>&1; do
if (( $(date +%s) >= deadline )); then
echo "service_recovery_failed timeout_s=${SERVICE_RECOVERY_TIMEOUT_S}"
return 1
fi
if [[ "$(docker inspect -f '{{.State.Running}}' "${CONTAINER}" 2>/dev/null || true)" != "true" ]]; then
echo "service_recovery_failed container_exited"
return 1
fi
sleep 10
done
echo "service_recovery=healthy container=${CONTAINER}"
}
add_failure_boundary() {
local failed_isl="$1" failed_osl="$2" failed_concurrency="$3" failed_scenario="$4" reason="$5"
touch "${FAILURE_BOUNDARIES_FILE}"
if ! awk -F '\t' -v i="${failed_isl}" -v o="${failed_osl}" -v c="${failed_concurrency}" \
'$1 == i && $2 == o && $3 == c { found=1 } END { exit !found }' \
"${FAILURE_BOUNDARIES_FILE}"; then
printf '%s\t%s\t%s\t%s\t%s\n' \
"${failed_isl}" "${failed_osl}" "${failed_concurrency}" "${failed_scenario}" "${reason}" \
>>"${FAILURE_BOUNDARIES_FILE}"
fi
}
strictly_above_failed_boundary() {
local candidate_isl="$1" candidate_osl="$2" candidate_concurrency="$3"
local failed_isl failed_osl failed_concurrency failed_scenario reason
[[ -s "${FAILURE_BOUNDARIES_FILE}" ]] || return 1
while IFS=$'\t' read -r failed_isl failed_osl failed_concurrency failed_scenario reason; do
if (( candidate_isl > failed_isl && candidate_osl > failed_osl && candidate_concurrency > failed_concurrency )); then
printf '%s' "${failed_scenario}"
return 0
fi
done <"${FAILURE_BOUNDARIES_FILE}"
return 1
}
failure_reason_from_log() {
local failure_log="$1"
if grep -q "Decode out of memory" "${failure_log}" 2>/dev/null; then
printf '%s' "kv_cache_decode_oom"
elif grep -qi "launch timed out and was terminated" "${failure_log}" 2>/dev/null; then
printf '%s' "xpu_kernel_launch_timeout"
elif grep -qiE "out of memory|OOM" "${failure_log}" 2>/dev/null; then
printf '%s' "out_of_memory"
elif grep -qiE "Xid|KL_XID|device.*error" "${failure_log}" 2>/dev/null; then
printf '%s' "xpu_device_error"
elif grep -qiE "watchdog|timeout" "${failure_log}" 2>/dev/null; then
printf '%s' "timeout_or_watchdog"
else
printf '%s' "bench_or_service_failure"
fi
}
echo "run_id=${RUN_ID} matrix_mode=${MATRIX_MODE} timeout=${SCENARIO_TIMEOUT_S}"
ensure_service
docker inspect "${CONTAINER}" >"${RESULT_DIR}/container_inspect.resume.$(date +%Y%m%d-%H%M%S).json"
if [[ ! -s "${RESULT_DIR}/scenarios.tsv" ]]; then
cp "${REFERENCE_DIR}/matrix.json" "${RESULT_DIR}/matrix.json"
python3 "${REFERENCE_DIR}/generate_scenarios.py" \
--matrix "${RESULT_DIR}/matrix.json" \
--mode "${MATRIX_MODE}" \
>"${RESULT_DIR}/scenarios.tsv"
fi
scenario_count="$(tail -n +2 "${RESULT_DIR}/scenarios.tsv" | wc -l)"
echo "scenario_count=${scenario_count}"
(
while true; do
date -u '+timestamp=%Y-%m-%dT%H:%M:%SZ'
xpu-smi
sleep 60
done
) >>"${RESULT_DIR}/xpu_monitor.log" 2>&1 &
monitor_pid=$!
trap 'kill "${monitor_pid}" >/dev/null 2>&1 || true' EXIT
index=0
tail -n +2 "${RESULT_DIR}/scenarios.tsv" | while IFS=$'\t' read -r mark isl osl concurrency num_prompts; do
index=$((index + 1))
scenario="c${concurrency}_i${isl}_o${osl}"
output_file="${RAW_DIR}/${scenario}.jsonl"
status_file="${LOG_DIR}/${scenario}.status"
detail_log="${LOG_DIR}/${scenario}.log"
if [[ -s "${output_file}" ]] && python3 "${RUN_DIR}/summarize_matrix.py" \
--check-completed "${output_file}" "${num_prompts}"; then
echo "[$index/$scenario_count] skip completed ${scenario}"
continue
fi
if [[ -s "${status_file}" ]] && grep -qE '^(failed|timeout)' "${status_file}"; then
existing_reason="previous_failure"
if [[ "${scenario}" == "c64_i8192_o2048" ]]; then
existing_reason="kv_cache_decode_oom"
fi
printf '%s\n' "${existing_reason}" >"${FAILURE_DIR}/${scenario}.reason"
add_failure_boundary "${isl}" "${osl}" "${concurrency}" "${scenario}" "${existing_reason}"
echo "[$index/$scenario_count] skip recorded failure ${scenario} reason=${existing_reason}"
continue
fi
failed_boundary=""
if failed_boundary="$(strictly_above_failed_boundary "${isl}" "${osl}" "${concurrency}")"; then
printf 'skipped\treason=strictly_above_failed_boundary\tboundary=%s\n' \
"${failed_boundary}" >"${status_file}"
echo "[$index/$scenario_count] skip strictly-above ${scenario} boundary=${failed_boundary}"
continue
fi
if ! ensure_service; then
echo "service_unrecoverable_before=${scenario}" | tee "${status_file}"
exit 1
fi
echo "[$index/$scenario_count] start mark=${mark} isl=${isl} osl=${osl} concurrency=${concurrency} prompts=${num_prompts}"
started="$(date +%s)"
started_iso="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
bench_rc=0
timeout "${SCENARIO_TIMEOUT_S}" docker exec "${CONTAINER}" env \
HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 HF_DATASETS_OFFLINE=1 \
"${PYTHON}" -m sglang.bench_serving \
--backend sglang \
--host 127.0.0.1 \
--port "${PORT}" \
--dataset-name random \
--dataset-path /workspace/ShareGPT_V3_unfiltered_cleaned_split.json \
--model /models \
--served-model-name GLM-5.2-w4a8 \
--tokenizer /models \
--random-input-len "${isl}" \
--random-output-len "${osl}" \
--random-range-ratio 1.0 \
--num-prompts "${num_prompts}" \
--max-concurrency "${concurrency}" \
--request-rate 10000 \
--seed 1 \
--flush-cache \
--output-file "/workspace/run/results/${RUN_ID}/raw_outputs/${scenario}.jsonl" \
--output-details \
>"${detail_log}" 2>&1 || bench_rc=$?
duration=$(( $(date +%s) - started ))
if [[ "${bench_rc}" -eq 0 ]]; then
printf 'completed\trc=0\tduration_s=%s\n' "${duration}" >"${status_file}"
echo "[$index/$scenario_count] completed ${scenario} duration_s=${duration}"
elif [[ "${bench_rc}" -eq 124 ]]; then
failure_log="${FAILURE_DIR}/${scenario}.server.log"
docker logs --since "${started_iso}" "${CONTAINER}" >"${failure_log}" 2>&1 || true
reason="$(failure_reason_from_log "${failure_log}")"
printf 'timeout\trc=124\tduration_s=%s\treason=%s\n' "${duration}" "${reason}" >"${status_file}"
printf '%s\n' "${reason}" >"${FAILURE_DIR}/${scenario}.reason"
add_failure_boundary "${isl}" "${osl}" "${concurrency}" "${scenario}" "${reason}"
echo "[$index/$scenario_count] timeout ${scenario} duration_s=${duration} reason=${reason}"
else
failure_log="${FAILURE_DIR}/${scenario}.server.log"
docker logs --since "${started_iso}" "${CONTAINER}" >"${failure_log}" 2>&1 || true
reason="$(failure_reason_from_log "${failure_log}")"
printf 'failed\trc=%s\tduration_s=%s\treason=%s\n' \
"${bench_rc}" "${duration}" "${reason}" >"${status_file}"
printf '%s\n' "${reason}" >"${FAILURE_DIR}/${scenario}.reason"
add_failure_boundary "${isl}" "${osl}" "${concurrency}" "${scenario}" "${reason}"
echo "[$index/$scenario_count] failed ${scenario} rc=${bench_rc} duration_s=${duration} reason=${reason}"
fi
python3 "${RUN_DIR}/summarize_matrix.py" \
--scenarios "${RESULT_DIR}/scenarios.tsv" \
--raw-dir "${RAW_DIR}" \
--log-dir "${LOG_DIR}" \
--output "${RESULT_DIR}/summary.tsv"
if ! curl --fail --silent --show-error --max-time 10 "http://127.0.0.1:${PORT}/health" >/dev/null; then
echo "service_unhealthy_after=${scenario}"
docker logs --tail 500 "${CONTAINER}" >"${FAILURE_DIR}/${scenario}.server_tail.log" 2>&1 || true
if ! ensure_service; then
echo "service_unrecoverable_after=${scenario}"
exit 1
fi
fi
done
python3 "${RUN_DIR}/summarize_matrix.py" \
--scenarios "${RESULT_DIR}/scenarios.tsv" \
--raw-dir "${RAW_DIR}" \
--log-dir "${LOG_DIR}" \
--output "${RESULT_DIR}/summary.tsv"
docker logs "${CONTAINER}" >"${RESULT_DIR}/server_after_matrix.log" 2>&1
echo "matrix_complete result_dir=${RESULT_DIR}"

118
experiments/p800/glm52_w4a8_sglang_tp8_single_node/run_full_matrix.sh.before-resume-20260818 Executable file
View File

@ -0,0 +1,118 @@
#!/usr/bin/env bash
set -Eeuo pipefail
CONTAINER="glm52-w4a8-tp8"
PORT="${PORT:-30000}"
RUN_DIR="/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke"
REFERENCE_DIR="/data1/wxy/sskj/experiments/p800/dsv4_p800_sglang_tp_dp_matrix"
RUN_ID="${RUN_ID:-$(date '+%Y%m%d-%H%M%S')-full-matrix}"
RESULT_DIR="${RUN_DIR}/results/${RUN_ID}"
RAW_DIR="${RESULT_DIR}/raw_outputs"
LOG_DIR="${RESULT_DIR}/logs"
PYTHON="/root/miniconda/envs/python310_torch25_cuda/bin/python"
SCENARIO_TIMEOUT_S="${SCENARIO_TIMEOUT_S:-28800}"
MATRIX_MODE="${MATRIX_MODE:-Y+P}"
mkdir -p "${RAW_DIR}" "${LOG_DIR}"
exec > >(tee -a "${RESULT_DIR}/orchestrator.log") 2>&1
echo "run_id=${RUN_ID} matrix_mode=${MATRIX_MODE} timeout=${SCENARIO_TIMEOUT_S}"
curl --fail --silent --show-error --max-time 10 "http://127.0.0.1:${PORT}/health" >/dev/null
docker inspect "${CONTAINER}" >"${RESULT_DIR}/container_inspect.json"
cp "${REFERENCE_DIR}/matrix.json" "${RESULT_DIR}/matrix.json"
python3 "${REFERENCE_DIR}/generate_scenarios.py" \
--matrix "${RESULT_DIR}/matrix.json" \
--mode "${MATRIX_MODE}" \
>"${RESULT_DIR}/scenarios.tsv"
scenario_count="$(tail -n +2 "${RESULT_DIR}/scenarios.tsv" | wc -l)"
echo "scenario_count=${scenario_count}"
(
while true; do
date -u '+timestamp=%Y-%m-%dT%H:%M:%SZ'
xpu-smi
sleep 60
done
) >"${RESULT_DIR}/xpu_monitor.log" 2>&1 &
monitor_pid=$!
trap 'kill "${monitor_pid}" >/dev/null 2>&1 || true' EXIT
index=0
tail -n +2 "${RESULT_DIR}/scenarios.tsv" | while IFS=$'\t' read -r mark isl osl concurrency num_prompts; do
index=$((index + 1))
scenario="c${concurrency}_i${isl}_o${osl}"
output_file="${RAW_DIR}/${scenario}.jsonl"
status_file="${LOG_DIR}/${scenario}.status"
detail_log="${LOG_DIR}/${scenario}.log"
if [[ -s "${output_file}" ]] && python3 "${RUN_DIR}/summarize_matrix.py" \
--check-completed "${output_file}" "${num_prompts}"; then
echo "[$index/$scenario_count] skip completed ${scenario}"
continue
fi
if ! curl --fail --silent --show-error --max-time 10 "http://127.0.0.1:${PORT}/health" >/dev/null; then
echo "service_unhealthy_before=${scenario}" | tee "${status_file}"
exit 1
fi
echo "[$index/$scenario_count] start mark=${mark} isl=${isl} osl=${osl} concurrency=${concurrency} prompts=${num_prompts}"
started="$(date +%s)"
bench_rc=0
timeout "${SCENARIO_TIMEOUT_S}" docker exec "${CONTAINER}" env \
HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 HF_DATASETS_OFFLINE=1 \
"${PYTHON}" -m sglang.bench_serving \
--backend sglang \
--host 127.0.0.1 \
--port "${PORT}" \
--dataset-name random \
--dataset-path /workspace/ShareGPT_V3_unfiltered_cleaned_split.json \
--model /models \
--served-model-name GLM-5.2-w4a8 \
--tokenizer /models \
--random-input-len "${isl}" \
--random-output-len "${osl}" \
--random-range-ratio 1.0 \
--num-prompts "${num_prompts}" \
--max-concurrency "${concurrency}" \
--request-rate 10000 \
--seed 1 \
--flush-cache \
--output-file "/workspace/run/results/${RUN_ID}/raw_outputs/${scenario}.jsonl" \
--output-details \
>"${detail_log}" 2>&1 || bench_rc=$?
duration=$(( $(date +%s) - started ))
if [[ "${bench_rc}" -eq 0 ]]; then
printf 'completed\trc=0\tduration_s=%s\n' "${duration}" >"${status_file}"
echo "[$index/$scenario_count] completed ${scenario} duration_s=${duration}"
elif [[ "${bench_rc}" -eq 124 ]]; then
printf 'timeout\trc=124\tduration_s=%s\n' "${duration}" >"${status_file}"
echo "[$index/$scenario_count] timeout ${scenario} duration_s=${duration}"
else
printf 'failed\trc=%s\tduration_s=%s\n' "${bench_rc}" "${duration}" >"${status_file}"
echo "[$index/$scenario_count] failed ${scenario} rc=${bench_rc} duration_s=${duration}"
fi
python3 "${RUN_DIR}/summarize_matrix.py" \
--scenarios "${RESULT_DIR}/scenarios.tsv" \
--raw-dir "${RAW_DIR}" \
--log-dir "${LOG_DIR}" \
--output "${RESULT_DIR}/summary.tsv"
if ! curl --fail --silent --show-error --max-time 10 "http://127.0.0.1:${PORT}/health" >/dev/null; then
echo "service_unhealthy_after=${scenario}"
docker logs --tail 500 "${CONTAINER}" >"${RESULT_DIR}/server_failure.log" 2>&1 || true
exit 1
fi
done
python3 "${RUN_DIR}/summarize_matrix.py" \
--scenarios "${RESULT_DIR}/scenarios.tsv" \
--raw-dir "${RAW_DIR}" \
--log-dir "${LOG_DIR}" \
--output "${RESULT_DIR}/summary.tsv"
docker logs "${CONTAINER}" >"${RESULT_DIR}/server_after_matrix.log" 2>&1
echo "matrix_complete result_dir=${RESULT_DIR}"

65
experiments/p800/glm52_w4a8_sglang_tp8_single_node/start_glm52_w4a8.sh Executable file
View File

@ -0,0 +1,65 @@
#!/usr/bin/env bash
set -Eeuo pipefail
IMAGE="iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746"
MODEL_DIR="/data2/GLM-5.2-w4a8"
DATASET="/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json"
RUN_DIR="/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke"
CONTAINER="glm52-w4a8-tp8"
PORT="${PORT:-30000}"
test -f "${MODEL_DIR}/config.json"
test -f "${DATASET}"
mkdir -p "${RUN_DIR}/results"
docker rm -f "${CONTAINER}" >/dev/null 2>&1 || true
docker run -d \
--init \
--name "${CONTAINER}" \
--privileged \
--ulimit core=-1 \
--security-opt seccomp=unconfined \
--net=host --uts=host --ipc=host \
--shm-size=256g \
-e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
-e XPU_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
-e CUDA_DISABLE_PRINTF=1 \
-e GLOO_SOCKET_TIMEOUT=60000 \
-v "${MODEL_DIR}:/models:ro" \
-v "${DATASET}:/workspace/ShareGPT_V3_unfiltered_cleaned_split.json:ro" \
-v "${RUN_DIR}:/workspace/run" \
-w /workspace/run \
"${IMAGE}" \
bash -lc "exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server \
--host 0.0.0.0 \
--port ${PORT} \
--model-path /models \
--served-model-name GLM-5.2-w4a8 \
--attention-backend nsa \
--nsa-prefill klxdsa \
--nsa-decode klxdsa \
--prefill-attention-backend klxdsa \
--decode-attention-backend klxdsa \
--trust-remote-code \
--disable-custom-all-reduce \
--disable-shared-experts-fusion \
--chunked-prefill-size 32768 \
--page-size 64 \
--mem-fraction-static 0.82 \
--max-prefill-tokens 32768 \
--max-running-requests 64 \
--tp-size 8 \
--ep-size 8 \
--quantization w4a8_int4 \
--kv-cache-dtype int8 \
--cuda-graph-max-bs 8 \
--disable-cuda-graph-padding \
--watchdog-timeout 3000000 \
--tool-call-parser glm47 \
--reasoning-parser glm45 \
--json-model-override-args '{\"index_topk_freq\": 4}' \
--allow-auto-truncate \
--enable-metrics"
echo "container=${CONTAINER} port=${PORT}"

64
experiments/p800/glm52_w4a8_sglang_tp8_single_node/start_glm52_w4a8.sh.before-init-20260818 Executable file
View File

@ -0,0 +1,64 @@
#!/usr/bin/env bash
set -Eeuo pipefail
IMAGE="iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260715_5746"
MODEL_DIR="/data2/GLM-5.2-w4a8"
DATASET="/data1/wxy/sskj/datasets/ShareGPT_V3_unfiltered_cleaned_split.json"
RUN_DIR="/data1/wxy/sskj/experiments/p800/glm52_w4a8_sglang_tp8_smoke"
CONTAINER="glm52-w4a8-tp8"
PORT="${PORT:-30000}"
test -f "${MODEL_DIR}/config.json"
test -f "${DATASET}"
mkdir -p "${RUN_DIR}/results"
docker rm -f "${CONTAINER}" >/dev/null 2>&1 || true
docker run -d \
--name "${CONTAINER}" \
--privileged \
--ulimit core=-1 \
--security-opt seccomp=unconfined \
--net=host --uts=host --ipc=host \
--shm-size=256g \
-e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
-e XPU_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
-e CUDA_DISABLE_PRINTF=1 \
-e GLOO_SOCKET_TIMEOUT=60000 \
-v "${MODEL_DIR}:/models:ro" \
-v "${DATASET}:/workspace/ShareGPT_V3_unfiltered_cleaned_split.json:ro" \
-v "${RUN_DIR}:/workspace/run" \
-w /workspace/run \
"${IMAGE}" \
bash -lc "exec /root/miniconda/envs/python310_torch25_cuda/bin/python -m sglang.launch_server \
--host 0.0.0.0 \
--port ${PORT} \
--model-path /models \
--served-model-name GLM-5.2-w4a8 \
--attention-backend nsa \
--nsa-prefill klxdsa \
--nsa-decode klxdsa \
--prefill-attention-backend klxdsa \
--decode-attention-backend klxdsa \
--trust-remote-code \
--disable-custom-all-reduce \
--disable-shared-experts-fusion \
--chunked-prefill-size 32768 \
--page-size 64 \
--mem-fraction-static 0.82 \
--max-prefill-tokens 32768 \
--max-running-requests 64 \
--tp-size 8 \
--ep-size 8 \
--quantization w4a8_int4 \
--kv-cache-dtype int8 \
--cuda-graph-max-bs 8 \
--disable-cuda-graph-padding \
--watchdog-timeout 3000000 \
--tool-call-parser glm47 \
--reasoning-parser glm45 \
--json-model-override-args '{\"index_topk_freq\": 4}' \
--allow-auto-truncate \
--enable-metrics"
echo "container=${CONTAINER} port=${PORT}"

71
experiments/p800/glm52_w4a8_sglang_tp8_single_node/summarize_matrix.py Executable file
View File

@ -0,0 +1,71 @@
#!/usr/bin/env python3
import argparse
import csv
import json
from pathlib import Path
def read_first_json(path: Path):
try:
with path.open("r", encoding="utf-8") as stream:
for line in stream:
line = line.strip()
if line:
return json.loads(line)
except (OSError, json.JSONDecodeError):
return None
return None
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--check-completed", nargs=2, metavar=("FILE", "EXPECTED"))
parser.add_argument("--scenarios")
parser.add_argument("--raw-dir")
parser.add_argument("--log-dir")
parser.add_argument("--output")
args = parser.parse_args()
if args.check_completed:
path, expected = args.check_completed
data = read_first_json(Path(path)) or {}
raise SystemExit(0 if int(data.get("completed", 0)) >= int(expected) else 1)
required = (args.scenarios, args.raw_dir, args.log_dir, args.output)
if not all(required):
parser.error("summary mode requires --scenarios, --raw-dir, --log-dir, and --output")
raw_dir = Path(args.raw_dir)
log_dir = Path(args.log_dir)
rows = []
with Path(args.scenarios).open("r", encoding="utf-8", newline="") as stream:
for scenario in csv.DictReader(stream, delimiter="\t"):
name = f"c{scenario['concurrency']}_i{scenario['input_len']}_o{scenario['output_len']}"
data = read_first_json(raw_dir / f"{name}.jsonl") or {}
status_path = log_dir / f"{name}.status"
status = status_path.read_text(encoding="utf-8").strip() if status_path.exists() else "pending"
rows.append({
**scenario,
"scenario": name,
"status": status,
"completed": data.get("completed", 0),
"duration_s": data.get("duration", ""),
"request_throughput": data.get("request_throughput", ""),
"input_throughput": data.get("input_throughput", ""),
"output_throughput": data.get("output_throughput", ""),
"total_token_throughput": data.get("total_token_throughput", ""),
"mean_ttft_ms": data.get("mean_ttft_ms", ""),
"p99_ttft_ms": data.get("p99_ttft_ms", ""),
"mean_tpot_ms": data.get("mean_tpot_ms", ""),
"p99_tpot_ms": data.get("p99_tpot_ms", ""),
})
fields = list(rows[0]) if rows else []
with Path(args.output).open("w", encoding="utf-8", newline="") as stream:
writer = csv.DictWriter(stream, fieldnames=fields, delimiter="\t")
writer.writeheader()
writer.writerows(rows)
if __name__ == "__main__":
main()