8b82f700e4
- Add experiments/dsv4_h200_sglang (config, server start, orchestrator, parser, README) - Fix start_server.sh to wait for HTTP 200 via curl --fail instead of treating 503 as ready - Add H200 SGLang baseline to root README and update .gitignore for per-run raw_outputs/logs - Remove stale experiments/dsv4_h200_dspark/DSPARK_FIX_PR_PREP.md
130 lines
3.9 KiB
JSON
130 lines
3.9 KiB
JSON
{
|
|
"metadata": {
|
|
"experiment": "dsv4_h200_sglang",
|
|
"run_id": "20260708-065101",
|
|
"timestamp": "2026-07-08T06:51:01+00:00",
|
|
"model": "/data/models/DeepSeek-V4-Flash",
|
|
"backend": "sglang",
|
|
"engine": "sglang",
|
|
"hardware": "8x NVIDIA H200 143GB",
|
|
"accelerator": "NVIDIA H200",
|
|
"chip": "nvidia_h200",
|
|
"script": "experiments/dsv4_h200_sglang/run_bench.sh",
|
|
"env": "/data/user1/yy/envs/sglang",
|
|
"git_commit": "7af3d4d",
|
|
"git_dirty": "dirty",
|
|
"description": "H200 native SGLang baseline benchmark for DeepSeek-V4-Flash"
|
|
},
|
|
"config": {
|
|
"tp": 8,
|
|
"moe_runner_backend": "marlin",
|
|
"port": 30006,
|
|
"num_prompts": 128,
|
|
"scenarios": [
|
|
"32 512 256",
|
|
"128 512 256"
|
|
]
|
|
},
|
|
"scenarios": [
|
|
{
|
|
"name": "c128_i512_o256",
|
|
"config": {
|
|
"concurrency": 128,
|
|
"input_len": 512,
|
|
"output_len": 256,
|
|
"dataset": "random",
|
|
"num_prompts": 128
|
|
},
|
|
"metrics": {
|
|
"success": 128,
|
|
"failed": 0,
|
|
"duration_s": 5.193163285992341,
|
|
"request_throughput": 24.647790364161636,
|
|
"input_token_throughput": 6787.38527153101,
|
|
"output_token_throughput": 3254.278571518216,
|
|
"total_token_throughput": 10041.663843049226,
|
|
"total_input_tokens": 35248,
|
|
"total_output_tokens": 16900,
|
|
"e2e_ms": {
|
|
"mean": 3471.4865707105673,
|
|
"p50": 3514.0166565033724,
|
|
"p90": 4998.641918299836,
|
|
"p95": 5056.324887800292,
|
|
"p99": 5112.00928252787
|
|
},
|
|
"ttft_ms": {
|
|
"mean": 924.1514429138533,
|
|
"p50": 849.3422594983713,
|
|
"p90": 1205.6520546015236,
|
|
"p95": 1207.7475340476667,
|
|
"p99": 1210.0433263290324
|
|
},
|
|
"tpot_ms": {
|
|
"mean": 26.29247494673112,
|
|
"p50": 19.806734621095913,
|
|
"p90": 35.49035216999157,
|
|
"p95": 46.297342646573306,
|
|
"p99": 145.35319635262547
|
|
},
|
|
"itl_ms": {
|
|
"mean": 19.44163585265753,
|
|
"p50": 15.339888006565161,
|
|
"p90": 17.66490399313625,
|
|
"p95": 18.918996000138577,
|
|
"p99": 153.02511929621687
|
|
}
|
|
},
|
|
"raw_file": "/data/user1/yy/experiments/dsv4_h200_sglang/results/20260708-065101/raw_outputs/sglang_0708_128_512_256.jsonl"
|
|
},
|
|
{
|
|
"name": "c32_i512_o256",
|
|
"config": {
|
|
"concurrency": 32,
|
|
"input_len": 512,
|
|
"output_len": 256,
|
|
"dataset": "random",
|
|
"num_prompts": 128
|
|
},
|
|
"metrics": {
|
|
"success": 128,
|
|
"failed": 0,
|
|
"duration_s": 22.31761664900114,
|
|
"request_throughput": 5.73537945440643,
|
|
"input_token_throughput": 1579.3801172571705,
|
|
"output_token_throughput": 757.2493185895989,
|
|
"total_token_throughput": 2336.6294358467694,
|
|
"total_input_tokens": 35248,
|
|
"total_output_tokens": 16900,
|
|
"e2e_ms": {
|
|
"mean": 5134.632653607923,
|
|
"p50": 4641.428427006758,
|
|
"p90": 9806.394101392652,
|
|
"p95": 10278.134901099836,
|
|
"p99": 10792.887551254826
|
|
},
|
|
"ttft_ms": {
|
|
"mean": 380.2895297493478,
|
|
"p50": 331.6603470011614,
|
|
"p90": 642.7646050986368,
|
|
"p95": 766.6534427480656,
|
|
"p99": 772.1964311384363
|
|
},
|
|
"tpot_ms": {
|
|
"mean": 36.81840456313315,
|
|
"p50": 38.839227149440994,
|
|
"p90": 44.66492350042031,
|
|
"p95": 48.50295195923065,
|
|
"p99": 60.81439458782757
|
|
},
|
|
"itl_ms": {
|
|
"mean": 36.28599313285003,
|
|
"p50": 11.074887996073812,
|
|
"p90": 154.03797599719837,
|
|
"p95": 164.296265997109,
|
|
"p99": 203.1443601998035
|
|
}
|
|
},
|
|
"raw_file": "/data/user1/yy/experiments/dsv4_h200_sglang/results/20260708-065101/raw_outputs/sglang_0708_32_512_256.jsonl"
|
|
}
|
|
]
|
|
} |