diff --git a/experiments/dsv4_p800_sglang/results/20260708-043404/results.json b/experiments/dsv4_p800_sglang/results/20260708-043404/results.json deleted file mode 100644 index 79f632f..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-043404/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-043404", - "timestamp": "2026-07-08T04:34:04+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} diff --git a/experiments/dsv4_p800_sglang/results/20260708-043830/results.json b/experiments/dsv4_p800_sglang/results/20260708-043830/results.json deleted file mode 100644 index 5335eef..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-043830/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-043830", - "timestamp": "2026-07-08T04:38:30+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} diff --git a/experiments/dsv4_p800_sglang/results/20260708-044535/results.json b/experiments/dsv4_p800_sglang/results/20260708-044535/results.json deleted file mode 100644 index 94df31b..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-044535/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-044535", - "timestamp": "2026-07-08T04:45:35+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} diff --git a/experiments/dsv4_p800_sglang/results/20260708-045327/results.json b/experiments/dsv4_p800_sglang/results/20260708-045327/results.json deleted file mode 100644 index f2b1bbe..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-045327/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-045327", - "timestamp": "2026-07-08T04:53:27+00:00", - "model": "/data1/models/deepseek-ai/DeepSeek-V4-Flash", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} diff --git a/experiments/dsv4_p800_sglang/results/20260708-045554/results.json b/experiments/dsv4_p800_sglang/results/20260708-045554/results.json deleted file mode 100644 index a95c6d2..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-045554/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-045554", - "timestamp": "2026-07-08T04:55:54+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} diff --git a/experiments/dsv4_p800_sglang/results/20260708-045616/results.json b/experiments/dsv4_p800_sglang/results/20260708-045616/results.json deleted file mode 100644 index 70013bf..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-045616/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-045616", - "timestamp": "2026-07-08T04:56:16+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} diff --git a/experiments/dsv4_p800_sglang/results/20260708-050025/results.json b/experiments/dsv4_p800_sglang/results/20260708-050025/results.json deleted file mode 100644 index 5ec902a..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-050025/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-050025", - "timestamp": "2026-07-08T05:00:25+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} diff --git a/experiments/dsv4_p800_sglang/results/20260708-050713/report.md b/experiments/dsv4_p800_sglang/results/20260708-050713/report.md deleted file mode 100644 index fe11a79..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-050713/report.md +++ /dev/null @@ -1,16 +0,0 @@ -# Benchmark Report: dsv4_p800_sglang - -## Metadata - -- **Run ID**: 20260708-050713 -- **Timestamp**: 2026-07-08T05:07:13+00:00 -- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800 -- **Engine/Backend**: sglang-xpu / sglang -- **Hardware**: 8x Kunlun P800 XPU -- **Model**: /data1/models/DeepSeek-V4-Flash-INT8 -- **Git Commit**: 2c332ff - -## Results - -| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 | -|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| diff --git a/experiments/dsv4_p800_sglang/results/20260708-050713/results.json b/experiments/dsv4_p800_sglang/results/20260708-050713/results.json deleted file mode 100644 index 06ec92b..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-050713/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-050713", - "timestamp": "2026-07-08T05:07:13+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} \ No newline at end of file diff --git a/experiments/dsv4_p800_sglang/results/20260708-050722/report.md b/experiments/dsv4_p800_sglang/results/20260708-050722/report.md deleted file mode 100644 index 9d497fe..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-050722/report.md +++ /dev/null @@ -1,16 +0,0 @@ -# Benchmark Report: dsv4_p800_sglang - -## Metadata - -- **Run ID**: 20260708-050722 -- **Timestamp**: 2026-07-08T05:07:22+00:00 -- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800 -- **Engine/Backend**: sglang-xpu / sglang -- **Hardware**: 8x Kunlun P800 XPU -- **Model**: /data1/models/DeepSeek-V4-Flash-INT8 -- **Git Commit**: 2c332ff - -## Results - -| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 | -|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| diff --git a/experiments/dsv4_p800_sglang/results/20260708-050722/results.json b/experiments/dsv4_p800_sglang/results/20260708-050722/results.json deleted file mode 100644 index 75d0b0f..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-050722/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-050722", - "timestamp": "2026-07-08T05:07:22+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} \ No newline at end of file diff --git a/experiments/dsv4_p800_sglang/results/20260708-050858/report.md b/experiments/dsv4_p800_sglang/results/20260708-050858/report.md deleted file mode 100644 index 7bfb506..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-050858/report.md +++ /dev/null @@ -1,16 +0,0 @@ -# Benchmark Report: dsv4_p800_sglang - -## Metadata - -- **Run ID**: 20260708-050858 -- **Timestamp**: 2026-07-08T05:08:58+00:00 -- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800 -- **Engine/Backend**: sglang-xpu / sglang -- **Hardware**: 8x Kunlun P800 XPU -- **Model**: /data1/models/DeepSeek-V4-Flash-INT8 -- **Git Commit**: 2c332ff - -## Results - -| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 | -|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| diff --git a/experiments/dsv4_p800_sglang/results/20260708-050858/results.json b/experiments/dsv4_p800_sglang/results/20260708-050858/results.json deleted file mode 100644 index 7978092..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-050858/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-050858", - "timestamp": "2026-07-08T05:08:58+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} \ No newline at end of file diff --git a/experiments/dsv4_p800_sglang/results/20260708-051023/report.md b/experiments/dsv4_p800_sglang/results/20260708-051023/report.md deleted file mode 100644 index 4baebbb..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-051023/report.md +++ /dev/null @@ -1,16 +0,0 @@ -# Benchmark Report: dsv4_p800_sglang - -## Metadata - -- **Run ID**: 20260708-051023 -- **Timestamp**: 2026-07-08T05:10:23+00:00 -- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800 -- **Engine/Backend**: sglang-xpu / sglang -- **Hardware**: 8x Kunlun P800 XPU -- **Model**: /data1/models/DeepSeek-V4-Flash-INT8 -- **Git Commit**: 2c332ff - -## Results - -| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 | -|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| diff --git a/experiments/dsv4_p800_sglang/results/20260708-051023/results.json b/experiments/dsv4_p800_sglang/results/20260708-051023/results.json deleted file mode 100644 index e0330b9..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-051023/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-051023", - "timestamp": "2026-07-08T05:10:23+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} \ No newline at end of file diff --git a/experiments/dsv4_p800_sglang/results/20260708-051200/results.json b/experiments/dsv4_p800_sglang/results/20260708-051200/results.json deleted file mode 100644 index b806584..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-051200/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-051200", - "timestamp": "2026-07-08T05:12:00+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} diff --git a/experiments/dsv4_p800_sglang/results/20260708-051316/report.md b/experiments/dsv4_p800_sglang/results/20260708-051316/report.md deleted file mode 100644 index 4a72f6c..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-051316/report.md +++ /dev/null @@ -1,17 +0,0 @@ -# Benchmark Report: dsv4_p800_sglang - -## Metadata - -- **Run ID**: 20260708-051316 -- **Timestamp**: 2026-07-08T05:13:16+00:00 -- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800 -- **Engine/Backend**: sglang-xpu / sglang -- **Hardware**: 8x Kunlun P800 XPU -- **Model**: /data1/models/DeepSeek-V4-Flash-INT8 -- **Git Commit**: 2c332ff - -## Results - -| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 | -|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| -| c32_i512_o256 | 32 | 512/256 | 10 | 0 | 1.87 | 262.65 | 506.4399079710711 | 507.2712521097855 | 21.948128755653826 | 29.154062995221466 | 5314.590020017349 | diff --git a/experiments/dsv4_p800_sglang/results/20260708-051316/results.json b/experiments/dsv4_p800_sglang/results/20260708-051316/results.json deleted file mode 100644 index 60b7466..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-051316/results.json +++ /dev/null @@ -1,2482 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-051316", - "timestamp": "2026-07-08T05:13:16+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "2c332ff", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [ - { - "name": "c32_i512_o256", - "concurrency": 32, - "input_len": 512, - "output_len": 256, - "success": 10, - "failed": 0, - "duration_s": 5.35, - "request_throughput": 1.87, - "input_token_throughput": 470.87, - "output_token_throughput": 262.65, - "total_token_throughput": 733.53, - "accept_length": null, - "latencies": { - "e2e_ms": { - "mean": 3372.781996097183, - "p50": 3498.675397480838, - "p90": 5125.400093087228, - "p95": null, - "p99": 5314.590020017349 - }, - "ttft_ms": { - "mean": 478.8548628857825, - "p50": 506.4399079710711, - "p90": null, - "p95": null, - "p99": 507.2712521097855 - }, - "tpot_ms": { - "mean": 22.334078483797782, - "p50": 21.948128755653826, - "p90": null, - "p95": null, - "p99": 29.154062995221466 - }, - "itl_ms": { - "mean": 20.75981864563044, - "p50": 18.560815330905218, - "p90": null, - "p95": 30.416983005125076, - "p99": 76.09861597185954 - } - }, - "raw_requests": [ - { - "tag": null, - "backend": "sglang", - "dataset_name": "random", - "request_rate": Infinity, - "max_concurrency": 32, - "sharegpt_output_len": null, - "random_input_len": 512, - "random_output_len": 256, - "random_range_ratio": 0.0, - "server_info": { - "model_path": "/data1/models/DeepSeek-V4-Flash-INT8", - "tokenizer_path": "/data1/models/DeepSeek-V4-Flash-INT8", - "tokenizer_mode": "auto", - "tokenizer_worker_num": 1, - "skip_tokenizer_init": false, - "load_format": "auto", - "model_loader_extra_config": "{}", - "trust_remote_code": true, - "context_length": null, - "is_embedding": false, - "enable_multimodal": null, - "revision": null, - "model_impl": "auto", - "host": "0.0.0.0", - "port": 30000, - "fastapi_root_path": "", - "grpc_mode": false, - "skip_server_warmup": false, - "warmups": null, - "nccl_port": null, - "checkpoint_engine_wait_weights_before_ready": false, - "ssl_keyfile": null, - "ssl_certfile": null, - "ssl_ca_certs": null, - "ssl_keyfile_password": null, - "enable_ssl_refresh": false, - "dtype": "auto", - "quantization": "w8a8_int8", - "quantization_param_path": null, - "kv_cache_dtype": "float16", - "enable_fp32_lm_head": false, - "modelopt_quant": null, - "modelopt_checkpoint_restore_path": null, - "modelopt_checkpoint_save_path": null, - "modelopt_export_path": null, - "quantize_and_serve": false, - "rl_quant_profile": null, - "mem_fraction_static": 0.8, - "max_running_requests": 64, - "max_queued_requests": null, - "max_total_tokens": null, - "chunked_prefill_size": 8192, - "enable_dynamic_chunking": false, - "max_prefill_tokens": 16384, - "prefill_max_requests": null, - "custom_max_context_len": null, - "schedule_policy": "fcfs", - "enable_priority_scheduling": false, - "disable_priority_preemption": false, - "default_priority_value": null, - "abort_on_priority_when_disabled": false, - "schedule_low_priority_values_first": false, - "priority_scheduling_preemption_threshold": 10, - "schedule_conservativeness": 1.0, - "page_size": 256, - "swa_full_tokens_ratio": 0.1, - "disable_hybrid_swa_memory": false, - "radix_eviction_policy": "lru", - "enable_prefill_delayer": false, - "prefill_delayer_max_delay_passes": 30, - "prefill_delayer_token_usage_low_watermark": null, - "prefill_delayer_forward_passes_buckets": null, - "prefill_delayer_wait_seconds_buckets": null, - "device": "cuda", - "tp_size": 8, - "pp_size": 1, - "pp_max_micro_batch_size": null, - "pp_async_batch_depth": 0, - "stream_interval": 1, - "stream_response_default_include_usage": false, - "incremental_streaming_output": false, - "enable_streaming_session": false, - "random_seed": 228424360, - "constrained_json_whitespace_pattern": null, - "constrained_json_disable_any_whitespace": true, - "watchdog_timeout": 3000000.0, - "soft_watchdog_timeout": null, - "dist_timeout": null, - "download_dir": null, - "model_checksum": null, - "base_gpu_id": 0, - "gpu_id_step": 1, - "sleep_on_idle": false, - "use_ray": false, - "custom_sigquit_handler": null, - "log_level": "info", - "log_level_http": null, - "log_requests": false, - "log_requests_level": 2, - "log_requests_format": "text", - "log_requests_target": null, - "uvicorn_access_log_exclude_prefixes": [], - "crash_dump_folder": null, - "show_time_cost": false, - "enable_metrics": true, - "enable_mfu_metrics": false, - "enable_metrics_for_all_schedulers": false, - "tokenizer_metrics_custom_labels_header": "x-custom-labels", - "tokenizer_metrics_allowed_custom_labels": null, - "extra_metric_labels": null, - "bucket_time_to_first_token": null, - "bucket_inter_token_latency": null, - "bucket_e2e_request_latency": null, - "collect_tokens_histogram": false, - "prompt_tokens_buckets": null, - "generation_tokens_buckets": null, - "gc_warning_threshold_secs": 0.0, - "decode_log_interval": 40, - "enable_request_time_stats_logging": true, - "kv_events_config": null, - "enable_trace": false, - "otlp_traces_endpoint": "localhost:4317", - "export_metrics_to_file": false, - "export_metrics_to_file_dir": null, - "api_key": null, - "admin_api_key": null, - "served_model_name": "/data1/models/DeepSeek-V4-Flash-INT8", - "weight_version": "default", - "chat_template": null, - "hf_chat_template_name": null, - "completion_template": null, - "file_storage_path": "sglang_storage", - "enable_cache_report": false, - "reasoning_parser": "deepseek-v4", - "tool_call_parser": "deepseekv4", - "tool_server": null, - "sampling_defaults": "model", - "dp_size": 1, - "load_balance_method": "round_robin", - "attn_cp_size": 1, - "moe_dp_size": 1, - "dist_init_addr": null, - "nnodes": 1, - "node_rank": 0, - "json_model_override_args": "{}", - "preferred_sampling_params": null, - "enable_lora": null, - "enable_lora_overlap_loading": null, - "max_lora_rank": null, - "lora_target_modules": null, - "lora_paths": null, - "max_loaded_loras": null, - "max_loras_per_batch": 8, - "lora_eviction_policy": "lru", - "lora_backend": "csgmv", - "max_lora_chunk_size": 16, - "experts_shared_outer_loras": null, - "attention_backend": "compressed", - "decode_attention_backend": null, - "prefill_attention_backend": null, - "sampling_backend": "flashinfer", - "grammar_backend": "xgrammar", - "mm_attention_backend": null, - "fp8_gemm_runner_backend": "auto", - "fp4_gemm_runner_backend": "auto", - "nsa_prefill_backend": "klxdsa", - "nsa_decode_backend": "klxdsa", - "disable_flashinfer_autotune": false, - "mamba_backend": "triton", - "speculative_algorithm": "EAGLE", - "speculative_draft_model_path": "/data1/models/DeepSeek-V4-Flash-INT8", - "speculative_draft_model_revision": null, - "speculative_draft_load_format": null, - "speculative_num_steps": 3, - "speculative_eagle_topk": 1, - "speculative_num_draft_tokens": 4, - "speculative_accept_threshold_single": 1.0, - "speculative_accept_threshold_acc": 1.0, - "speculative_token_map": null, - "speculative_attention_mode": "prefill", - "speculative_draft_attention_backend": null, - "speculative_moe_runner_backend": "auto", - "speculative_moe_a2a_backend": null, - "speculative_draft_model_quantization": "w8a8_int8", - "speculative_ngram_min_bfs_breadth": 1, - "speculative_ngram_max_bfs_breadth": 10, - "speculative_ngram_match_type": "BFS", - "speculative_ngram_max_trie_depth": 18, - "speculative_ngram_capacity": 10000000, - "enable_multi_layer_eagle": false, - "ep_size": 8, - "moe_a2a_backend": "none", - "moe_runner_backend": "auto", - "flashinfer_mxfp4_moe_precision": "default", - "enable_hisparse": false, - "enable_flashinfer_allreduce_fusion": false, - "enforce_disable_flashinfer_allreduce_fusion": false, - "enable_aiter_allreduce_fusion": false, - "deepep_mode": "auto", - "ep_num_redundant_experts": 0, - "ep_dispatch_algorithm": null, - "init_expert_location": "trivial", - "enable_eplb": false, - "eplb_algorithm": "auto", - "eplb_rebalance_num_iterations": 1000, - "eplb_rebalance_layers_per_chunk": null, - "eplb_min_rebalancing_utilization_threshold": 1.0, - "expert_distribution_recorder_mode": null, - "expert_distribution_recorder_buffer_size": 1000, - "enable_expert_distribution_metrics": false, - "deepep_config": null, - "moe_dense_tp_size": null, - "elastic_ep_backend": null, - "enable_elastic_expert_backup": false, - "mooncake_ib_device": null, - "max_mamba_cache_size": null, - "mamba_ssm_dtype": null, - "mamba_full_memory_ratio": 0.9, - "mamba_scheduler_strategy": "no_buffer", - "mamba_track_interval": 256, - "linear_attn_backend": "triton", - "linear_attn_decode_backend": null, - "linear_attn_prefill_backend": null, - "enable_hierarchical_cache": false, - "hicache_ratio": 2.0, - "hicache_size": 0, - "hicache_write_policy": "write_through", - "hicache_io_backend": "kernel", - "hicache_mem_layout": "page_first", - "hicache_storage_backend": null, - "hicache_storage_prefetch_policy": "best_effort", - "hicache_storage_backend_extra_config": null, - "hisparse_config": null, - "enable_lmcache": false, - "kt_weight_path": null, - "kt_method": "AMXINT4", - "kt_cpuinfer": null, - "kt_threadpool_count": 2, - "kt_num_gpu_experts": null, - "kt_max_deferred_experts_per_token": null, - "dllm_algorithm": null, - "dllm_algorithm_config": null, - "enable_double_sparsity": false, - "ds_channel_config_path": null, - "ds_heavy_channel_num": 32, - "ds_heavy_token_num": 256, - "ds_heavy_channel_type": "qk", - "ds_sparse_decode_threshold": 4096, - "cpu_offload_gb": 0, - "offload_group_size": -1, - "offload_num_in_group": 1, - "offload_prefetch_step": 1, - "offload_mode": "cpu", - "multi_item_scoring_delimiter": null, - "disable_radix_cache": false, - "cuda_graph_max_bs": 32, - "cuda_graph_bs": [ - 1, - 2, - 3, - 4, - 5, - 6, - 7, - 8, - 10, - 12, - 14, - 16, - 18, - 20, - 22, - 24, - 26, - 28, - 30, - 32 - ], - "disable_cuda_graph": false, - "disable_cuda_graph_padding": false, - "enable_profile_cuda_graph": false, - "enable_cudagraph_gc": false, - "enable_layerwise_nvtx_marker": false, - "enable_nccl_nvls": false, - "enable_symm_mem": false, - "disable_flashinfer_cutlass_moe_fp4_allgather": false, - "enable_tokenizer_batch_encode": false, - "disable_tokenizer_batch_decode": false, - "disable_outlines_disk_cache": false, - "disable_custom_all_reduce": true, - "enable_mscclpp": false, - "enable_torch_symm_mem": false, - "pre_warm_nccl": false, - "disable_overlap_schedule": false, - "enable_mixed_chunk": false, - "enable_dp_attention": false, - "enable_dp_lm_head": false, - "enable_two_batch_overlap": false, - "enable_single_batch_overlap": false, - "tbo_token_distribution_threshold": 0.48, - "enable_torch_compile": false, - "disable_piecewise_cuda_graph": true, - "enforce_piecewise_cuda_graph": false, - "enable_torch_compile_debug_mode": false, - "torch_compile_max_bs": 32, - "piecewise_cuda_graph_max_tokens": 8192, - "piecewise_cuda_graph_tokens": [ - 4, - 8, - 12, - 16, - 20, - 24, - 28, - 32, - 48, - 64, - 80, - 96, - 112, - 128, - 144, - 160, - 176, - 192, - 208, - 224, - 240, - 256, - 288, - 320, - 352, - 384, - 416, - 448, - 480, - 512, - 576, - 640, - 704, - 768, - 832, - 896, - 960, - 1024, - 1280, - 1536, - 1792, - 2048, - 2304, - 2560, - 2816, - 3072, - 3328, - 3584, - 3840, - 4096, - 4608, - 5120, - 5632, - 6144, - 6656, - 7168, - 7680, - 8192 - ], - "piecewise_cuda_graph_compiler": "eager", - "torchao_config": "", - "enable_nan_detection": false, - "enable_p2p_check": false, - "triton_attention_reduce_in_fp32": false, - "triton_attention_num_kv_splits": 8, - "triton_attention_split_tile_size": null, - "num_continuous_decode_steps": 1, - "delete_ckpt_after_loading": false, - "enable_memory_saver": false, - "enable_weights_cpu_backup": false, - "enable_draft_weights_cpu_backup": false, - "allow_auto_truncate": false, - "enable_custom_logit_processor": false, - "flashinfer_mla_disable_ragged": false, - "disable_shared_experts_fusion": true, - "disable_chunked_prefix_cache": false, - "disable_fast_image_processor": false, - "keep_mm_feature_on_device": false, - "enable_return_hidden_states": false, - "enable_return_routed_experts": false, - "enable_return_indexer_topk": false, - "scheduler_recv_interval": 1, - "numa_node": null, - "enable_deterministic_inference": false, - "rl_on_policy_target": null, - "enable_attn_tp_input_scattered": false, - "gc_threshold": null, - "enable_nsa_prefill_context_parallel": false, - "nsa_prefill_cp_mode": "in-seq-split", - "enable_fused_qk_norm_rope": false, - "enable_precise_embedding_interpolation": false, - "enable_fused_moe_sum_all_reduce": false, - "enable_prefill_context_parallel": false, - "prefill_cp_mode": "in-seq-split", - "enable_dynamic_batch_tokenizer": false, - "dynamic_batch_tokenizer_batch_size": 32, - "dynamic_batch_tokenizer_batch_timeout": 0.002, - "debug_tensor_dump_output_folder": null, - "debug_tensor_dump_layers": null, - "debug_tensor_dump_input_file": null, - "debug_tensor_dump_inject": false, - "disaggregation_mode": "null", - "disaggregation_transfer_backend": "mooncake", - "disaggregation_bootstrap_port": 8998, - "disaggregation_ib_device": null, - "disaggregation_decode_enable_offload_kvcache": false, - "num_reserved_decode_tokens": 512, - "disaggregation_decode_polling_interval": 1, - "encoder_only": false, - "language_only": false, - "encoder_transfer_backend": "zmq_to_scheduler", - "encoder_urls": [], - "enable_adaptive_dispatch_to_encoder": false, - "enable_over_encoding": false, - "enable_kv_mirror": false, - "custom_weight_loader": [], - "weight_loader_disable_mmap": false, - "remote_instance_weight_loader_seed_instance_ip": null, - "remote_instance_weight_loader_seed_instance_service_port": null, - "remote_instance_weight_loader_send_weights_group_ports": null, - "remote_instance_weight_loader_backend": "nccl", - "remote_instance_weight_loader_start_seed_via_transfer_engine": false, - "engine_info_bootstrap_port": 6789, - "modelexpress_config": null, - "enable_pdmux": false, - "pdmux_config_path": null, - "sm_group_num": 8, - "enable_broadcast_mm_inputs_process": false, - "enable_prefix_mm_cache": false, - "mm_enable_dp_encoder": false, - "mm_process_config": {}, - "limit_mm_data_per_request": null, - "enable_mm_global_cache": false, - "decrypted_config_file": null, - "decrypted_draft_config_file": null, - "forward_hooks": null, - "index_cache_topk_freq": 1, - "index_cache_pattern": null, - "status": "ready", - "max_total_num_tokens": 1593344, - "max_req_input_len": 1048570, - "internal_states": [ - { - "model_path": "/data1/models/DeepSeek-V4-Flash-INT8", - "tokenizer_path": "/data1/models/DeepSeek-V4-Flash-INT8", - "tokenizer_mode": "auto", - "tokenizer_worker_num": 1, - "skip_tokenizer_init": false, - "load_format": "auto", - "model_loader_extra_config": "{}", - "trust_remote_code": true, - "context_length": 1048576, - "is_embedding": false, - "enable_multimodal": null, - "revision": null, - "model_impl": "auto", - "host": "0.0.0.0", - "port": 30000, - "fastapi_root_path": "", - "grpc_mode": false, - "skip_server_warmup": false, - "warmups": null, - "nccl_port": null, - "checkpoint_engine_wait_weights_before_ready": false, - "ssl_keyfile": null, - "ssl_certfile": null, - "ssl_ca_certs": null, - "ssl_keyfile_password": null, - "enable_ssl_refresh": false, - "dtype": "auto", - "quantization": "w8a8_int8", - "quantization_param_path": null, - "kv_cache_dtype": "float16", - "enable_fp32_lm_head": false, - "modelopt_quant": null, - "modelopt_checkpoint_restore_path": null, - "modelopt_checkpoint_save_path": null, - "modelopt_export_path": null, - "quantize_and_serve": false, - "rl_quant_profile": null, - "mem_fraction_static": 0.8, - "max_running_requests": 64, - "max_queued_requests": null, - "max_total_tokens": null, - "chunked_prefill_size": 8192, - "enable_dynamic_chunking": false, - "max_prefill_tokens": 16384, - "prefill_max_requests": null, - "custom_max_context_len": null, - "schedule_policy": "fcfs", - "enable_priority_scheduling": false, - "disable_priority_preemption": false, - "default_priority_value": null, - "abort_on_priority_when_disabled": false, - "schedule_low_priority_values_first": false, - "priority_scheduling_preemption_threshold": 10, - "schedule_conservativeness": 1.0, - "page_size": 256, - "swa_full_tokens_ratio": 0.1, - "disable_hybrid_swa_memory": false, - "radix_eviction_policy": "lru", - "enable_prefill_delayer": false, - "prefill_delayer_max_delay_passes": 30, - "prefill_delayer_token_usage_low_watermark": null, - "prefill_delayer_forward_passes_buckets": null, - "prefill_delayer_wait_seconds_buckets": null, - "device": "cuda", - "tp_size": 8, - "pp_size": 1, - "pp_max_micro_batch_size": 64, - "pp_async_batch_depth": 0, - "stream_interval": 1, - "stream_response_default_include_usage": false, - "incremental_streaming_output": false, - "enable_streaming_session": false, - "random_seed": 228424360, - "constrained_json_whitespace_pattern": null, - "constrained_json_disable_any_whitespace": true, - "watchdog_timeout": 3000000.0, - "soft_watchdog_timeout": null, - "dist_timeout": null, - "download_dir": null, - "model_checksum": null, - "base_gpu_id": 0, - "gpu_id_step": 1, - "sleep_on_idle": false, - "use_ray": false, - "custom_sigquit_handler": null, - "log_level": "info", - "log_level_http": null, - "log_requests": false, - "log_requests_level": 2, - "log_requests_format": "text", - "log_requests_target": null, - "uvicorn_access_log_exclude_prefixes": [], - "crash_dump_folder": null, - "show_time_cost": false, - "enable_metrics": true, - "enable_mfu_metrics": false, - "enable_metrics_for_all_schedulers": false, - "tokenizer_metrics_custom_labels_header": "x-custom-labels", - "tokenizer_metrics_allowed_custom_labels": null, - "extra_metric_labels": null, - "bucket_time_to_first_token": null, - "bucket_inter_token_latency": null, - "bucket_e2e_request_latency": null, - "collect_tokens_histogram": false, - "prompt_tokens_buckets": null, - "generation_tokens_buckets": null, - "gc_warning_threshold_secs": 0.0, - "decode_log_interval": 40, - "enable_request_time_stats_logging": true, - "kv_events_config": null, - "enable_trace": false, - "otlp_traces_endpoint": "localhost:4317", - "export_metrics_to_file": false, - "export_metrics_to_file_dir": null, - "api_key": null, - "admin_api_key": null, - "served_model_name": "/data1/models/DeepSeek-V4-Flash-INT8", - "weight_version": "default", - "chat_template": null, - "hf_chat_template_name": null, - "completion_template": null, - "file_storage_path": "sglang_storage", - "enable_cache_report": false, - "reasoning_parser": "deepseek-v4", - "tool_call_parser": "deepseekv4", - "tool_server": null, - "sampling_defaults": "model", - "dp_size": 1, - "load_balance_method": "round_robin", - "attn_cp_size": 1, - "moe_dp_size": 1, - "dist_init_addr": null, - "nnodes": 1, - "node_rank": 0, - "json_model_override_args": "{}", - "preferred_sampling_params": null, - "enable_lora": null, - "enable_lora_overlap_loading": null, - "max_lora_rank": null, - "lora_target_modules": null, - "lora_paths": null, - "max_loaded_loras": null, - "max_loras_per_batch": 8, - "lora_eviction_policy": "lru", - "lora_backend": "csgmv", - "max_lora_chunk_size": 16, - "experts_shared_outer_loras": null, - "attention_backend": "compressed", - "decode_attention_backend": "compressed", - "prefill_attention_backend": "compressed", - "sampling_backend": "flashinfer", - "grammar_backend": "xgrammar", - "mm_attention_backend": null, - "fp8_gemm_runner_backend": "auto", - "fp4_gemm_runner_backend": "auto", - "nsa_prefill_backend": "klxdsa", - "nsa_decode_backend": "klxdsa", - "disable_flashinfer_autotune": false, - "mamba_backend": "triton", - "speculative_algorithm": "EAGLE", - "speculative_draft_model_path": "/data1/models/DeepSeek-V4-Flash-INT8", - "speculative_draft_model_revision": null, - "speculative_draft_load_format": null, - "speculative_num_steps": 3, - "speculative_eagle_topk": 1, - "speculative_num_draft_tokens": 4, - "speculative_accept_threshold_single": 1.0, - "speculative_accept_threshold_acc": 1.0, - "speculative_token_map": null, - "speculative_attention_mode": "prefill", - "speculative_draft_attention_backend": null, - "speculative_moe_runner_backend": "auto", - "speculative_moe_a2a_backend": null, - "speculative_draft_model_quantization": "w8a8_int8", - "speculative_ngram_min_bfs_breadth": 1, - "speculative_ngram_max_bfs_breadth": 10, - "speculative_ngram_match_type": "BFS", - "speculative_ngram_max_trie_depth": 18, - "speculative_ngram_capacity": 10000000, - "enable_multi_layer_eagle": false, - "ep_size": 8, - "moe_a2a_backend": "none", - "moe_runner_backend": "auto", - "flashinfer_mxfp4_moe_precision": "default", - "enable_hisparse": false, - "enable_flashinfer_allreduce_fusion": false, - "enforce_disable_flashinfer_allreduce_fusion": false, - "enable_aiter_allreduce_fusion": false, - "deepep_mode": "auto", - "ep_num_redundant_experts": 0, - "ep_dispatch_algorithm": null, - "init_expert_location": "trivial", - "enable_eplb": false, - "eplb_algorithm": "auto", - "eplb_rebalance_num_iterations": 1000, - "eplb_rebalance_layers_per_chunk": null, - "eplb_min_rebalancing_utilization_threshold": 1.0, - "expert_distribution_recorder_mode": null, - "expert_distribution_recorder_buffer_size": 1000, - "enable_expert_distribution_metrics": false, - "deepep_config": null, - "moe_dense_tp_size": null, - "elastic_ep_backend": null, - "enable_elastic_expert_backup": false, - "mooncake_ib_device": null, - "max_mamba_cache_size": null, - "mamba_ssm_dtype": null, - "mamba_full_memory_ratio": 0.9, - "mamba_scheduler_strategy": "no_buffer", - "mamba_track_interval": 256, - "linear_attn_backend": "triton", - "linear_attn_decode_backend": null, - "linear_attn_prefill_backend": null, - "enable_hierarchical_cache": false, - "hicache_ratio": 2.0, - "hicache_size": 0, - "hicache_write_policy": "write_through", - "hicache_io_backend": "kernel", - "hicache_mem_layout": "page_first", - "hicache_storage_backend": null, - "hicache_storage_prefetch_policy": "best_effort", - "hicache_storage_backend_extra_config": null, - "hisparse_config": null, - "enable_lmcache": false, - "kt_weight_path": null, - "kt_method": "AMXINT4", - "kt_cpuinfer": null, - "kt_threadpool_count": 2, - "kt_num_gpu_experts": null, - "kt_max_deferred_experts_per_token": null, - "dllm_algorithm": null, - "dllm_algorithm_config": null, - "enable_double_sparsity": false, - "ds_channel_config_path": null, - "ds_heavy_channel_num": 32, - "ds_heavy_token_num": 256, - "ds_heavy_channel_type": "qk", - "ds_sparse_decode_threshold": 4096, - "cpu_offload_gb": 0, - "offload_group_size": -1, - "offload_num_in_group": 1, - "offload_prefetch_step": 1, - "offload_mode": "cpu", - "multi_item_scoring_delimiter": null, - "disable_radix_cache": false, - "cuda_graph_max_bs": 32, - "cuda_graph_bs": [ - 1, - 2, - 3, - 4, - 5, - 6, - 7, - 8, - 10, - 12, - 14, - 16, - 18, - 20, - 22, - 24, - 26, - 28, - 30, - 32 - ], - "disable_cuda_graph": false, - "disable_cuda_graph_padding": false, - "enable_profile_cuda_graph": false, - "enable_cudagraph_gc": false, - "enable_layerwise_nvtx_marker": false, - "enable_nccl_nvls": false, - "enable_symm_mem": false, - "disable_flashinfer_cutlass_moe_fp4_allgather": false, - "enable_tokenizer_batch_encode": false, - "disable_tokenizer_batch_decode": false, - "disable_outlines_disk_cache": false, - "disable_custom_all_reduce": true, - "enable_mscclpp": false, - "enable_torch_symm_mem": false, - "pre_warm_nccl": false, - "disable_overlap_schedule": false, - "enable_mixed_chunk": false, - "enable_dp_attention": false, - "enable_dp_lm_head": false, - "enable_two_batch_overlap": false, - "enable_single_batch_overlap": false, - "tbo_token_distribution_threshold": 0.48, - "enable_torch_compile": false, - "disable_piecewise_cuda_graph": true, - "enforce_piecewise_cuda_graph": false, - "enable_torch_compile_debug_mode": false, - "torch_compile_max_bs": 32, - "piecewise_cuda_graph_max_tokens": 8192, - "piecewise_cuda_graph_tokens": [ - 4, - 8, - 12, - 16, - 20, - 24, - 28, - 32, - 48, - 64, - 80, - 96, - 112, - 128, - 144, - 160, - 176, - 192, - 208, - 224, - 240, - 256, - 288, - 320, - 352, - 384, - 416, - 448, - 480, - 512, - 576, - 640, - 704, - 768, - 832, - 896, - 960, - 1024, - 1280, - 1536, - 1792, - 2048, - 2304, - 2560, - 2816, - 3072, - 3328, - 3584, - 3840, - 4096, - 4608, - 5120, - 5632, - 6144, - 6656, - 7168, - 7680, - 8192 - ], - "piecewise_cuda_graph_compiler": "eager", - "torchao_config": "", - "enable_nan_detection": false, - "enable_p2p_check": false, - "triton_attention_reduce_in_fp32": false, - "triton_attention_num_kv_splits": 8, - "triton_attention_split_tile_size": null, - "num_continuous_decode_steps": 1, - "delete_ckpt_after_loading": false, - "enable_memory_saver": false, - "enable_weights_cpu_backup": false, - "enable_draft_weights_cpu_backup": false, - "allow_auto_truncate": false, - "enable_custom_logit_processor": false, - "flashinfer_mla_disable_ragged": false, - "disable_shared_experts_fusion": true, - "disable_chunked_prefix_cache": true, - "disable_fast_image_processor": false, - "keep_mm_feature_on_device": false, - "enable_return_hidden_states": false, - "enable_return_routed_experts": false, - "enable_return_indexer_topk": false, - "scheduler_recv_interval": 1, - "numa_node": null, - "enable_deterministic_inference": false, - "rl_on_policy_target": null, - "enable_attn_tp_input_scattered": false, - "gc_threshold": null, - "enable_nsa_prefill_context_parallel": false, - "nsa_prefill_cp_mode": "in-seq-split", - "enable_fused_qk_norm_rope": false, - "enable_precise_embedding_interpolation": false, - "enable_fused_moe_sum_all_reduce": false, - "enable_prefill_context_parallel": false, - "prefill_cp_mode": "in-seq-split", - "enable_dynamic_batch_tokenizer": false, - "dynamic_batch_tokenizer_batch_size": 32, - "dynamic_batch_tokenizer_batch_timeout": 0.002, - "debug_tensor_dump_output_folder": null, - "debug_tensor_dump_layers": null, - "debug_tensor_dump_input_file": null, - "debug_tensor_dump_inject": false, - "disaggregation_mode": "null", - "disaggregation_transfer_backend": "mooncake", - "disaggregation_bootstrap_port": 8998, - "disaggregation_ib_device": null, - "disaggregation_decode_enable_offload_kvcache": false, - "num_reserved_decode_tokens": 512, - "disaggregation_decode_polling_interval": 1, - "encoder_only": false, - "language_only": false, - "encoder_transfer_backend": "zmq_to_scheduler", - "encoder_urls": [], - "enable_adaptive_dispatch_to_encoder": false, - "enable_over_encoding": false, - "enable_kv_mirror": false, - "custom_weight_loader": [], - "weight_loader_disable_mmap": false, - "remote_instance_weight_loader_seed_instance_ip": null, - "remote_instance_weight_loader_seed_instance_service_port": null, - "remote_instance_weight_loader_send_weights_group_ports": null, - "remote_instance_weight_loader_backend": "nccl", - "remote_instance_weight_loader_start_seed_via_transfer_engine": false, - "engine_info_bootstrap_port": 6789, - "modelexpress_config": null, - "enable_pdmux": false, - "pdmux_config_path": null, - "sm_group_num": 8, - "enable_broadcast_mm_inputs_process": false, - "enable_prefix_mm_cache": false, - "mm_enable_dp_encoder": false, - "mm_process_config": {}, - "limit_mm_data_per_request": null, - "enable_mm_global_cache": false, - "decrypted_config_file": null, - "decrypted_draft_config_file": null, - "forward_hooks": null, - "index_cache_topk_freq": 1, - "index_cache_pattern": null, - "use_mla_backend": false, - "_mx_config_cache": {}, - "_draft_pool_config": { - "full_max_total_num_tokens": 1593344, - "swa_max_total_num_tokens": 159232 - }, - "last_gen_throughput": 304.3209280340091, - "memory_usage": { - "weight": 37.94, - "kvcache": 0, - "token_capacity": 1593344, - "graph": 1.2 - }, - "effective_max_running_requests_per_dp": 64, - "avg_spec_accept_length": 2.8933333333333335 - } - ], - "version": "0.5.10+ee6948cf8" - }, - "duration": 5.34541754698148, - "completed": 10, - "total_input_tokens": 2517, - "total_input_text_tokens": 2517, - "total_input_vision_tokens": 0, - "total_output_tokens": 1404, - "total_output_tokens_retokenized": 1404, - "request_throughput": 1.870761247762007, - "input_throughput": 470.8706060616972, - "output_throughput": 262.6548791857858, - "total_throughput": 733.525485247483, - "mean_e2e_latency_ms": 3372.781996097183, - "median_e2e_latency_ms": 3498.675397480838, - "std_e2e_latency_ms": 1426.9563106485741, - "p90_e2e_latency_ms": 5125.400093087228, - "p99_e2e_latency_ms": 5314.590020017349, - "mean_ttft_ms": 478.8548628857825, - "median_ttft_ms": 506.4399079710711, - "std_ttft_ms": 82.89120389713447, - "p99_ttft_ms": 507.2712521097855, - "mean_tpot_ms": 22.334078483797782, - "median_tpot_ms": 21.948128755653826, - "std_tpot_ms": 3.1100348959353536, - "p99_tpot_ms": 29.154062995221466, - "mean_itl_ms": 20.75981864563044, - "median_itl_ms": 18.560815330905218, - "std_itl_ms": 11.544034313142475, - "p95_itl_ms": 30.416983005125076, - "p99_itl_ms": 76.09861597185954, - "concurrency": 6.309669855447998, - "accept_length": 2.8933333333333335, - "max_output_tokens_per_s": 396.0, - "max_concurrent_requests": 10, - "input_lens": [ - 38, - 236, - 397, - 73, - 256, - 394, - 204, - 134, - 336, - 449 - ], - "output_lens": [ - 145, - 130, - 205, - 72, - 238, - 253, - 135, - 26, - 179, - 21 - ], - "ttfts": [ - 0.23018694896018133, - 0.5072830729768611, - 0.5071517300093547, - 0.506980306992773, - 0.5067555939895101, - 0.5065123789827339, - 0.5063674369594082, - 0.5061119620222598, - 0.5057157859555446, - 0.5054834120091982 - ], - "itls": [ - [ - 0.1265941219899105, - 0.1265941219899105, - 0.1265941219899105, - 0.1265941219899105, - 0.03003738750703633, - 0.03003738750703633, - 0.020075495665272076, - 0.020075495665272076, - 0.020075495665272076, - 0.020034517995857943, - 0.020034517995857943, - 0.020034517995857943, - 0.020025947674488027, - 0.020025947674488027, - 0.020025947674488027, - 0.01982437400147319, - 0.01982437400147319, - 0.01982437400147319, - 0.030580375489080325, - 0.030580375489080325, - 0.015474200758035295, - 0.015474200758035295, - 0.015474200758035295, - 0.015474200758035295, - 0.02975128698744811, - 0.02975128698744811, - 0.018891388666816056, - 0.018891388666816056, - 0.018891388666816056, - 0.030985667331454653, - 0.030985667331454653, - 0.030985667331454653, - 0.01450748200295493, - 0.01450748200295493, - 0.01450748200295493, - 0.01450748200295493, - 0.02843167950049974, - 0.02843167950049974, - 0.019097025661418836, - 0.019097025661418836, - 0.019097025661418836, - 0.019033391009240102, - 0.019033391009240102, - 0.019033391009240102, - 0.02840644898242317, - 0.02840644898242317, - 0.0287785355176311, - 0.0287785355176311, - 0.01427662099013105, - 0.01427662099013105, - 0.01427662099013105, - 0.01427662099013105, - 0.028972148516913876, - 0.028972148516913876, - 0.0198178769981799, - 0.0198178769981799, - 0.0198178769981799, - 0.019058960994395118, - 0.019058960994395118, - 0.019058960994395118, - 0.014342486509121954, - 0.014342486509121954, - 0.014342486509121954, - 0.014342486509121954, - 0.028646462480537593, - 0.028646462480537593, - 0.01456742275331635, - 0.01456742275331635, - 0.01456742275331635, - 0.01456742275331635, - 0.01943501700103904, - 0.01943501700103904, - 0.01943501700103904, - 0.02791283550322987, - 0.02791283550322987, - 0.013792212252155878, - 0.013792212252155878, - 0.013792212252155878, - 0.013792212252155878, - 0.018324121988068025, - 0.018324121988068025, - 0.018324121988068025, - 0.018392249670190115, - 0.018392249670190115, - 0.018392249670190115, - 0.018568886327557266, - 0.018568886327557266, - 0.018568886327557266, - 0.018351545673795044, - 0.018351545673795044, - 0.018351545673795044, - 0.02752352401148528, - 0.02752352401148528, - 0.013863828251487575, - 0.013863828251487575, - 0.013863828251487575, - 0.013863828251487575, - 0.018301511649042368, - 0.018301511649042368, - 0.018301511649042368, - 0.027680501516442746, - 0.027680501516442746, - 0.01841827033786103, - 0.01841827033786103, - 0.01841827033786103, - 0.01374593649234157, - 0.01374593649234157, - 0.01374593649234157, - 0.01374593649234157, - 0.018055193999316543, - 0.018055193999316543, - 0.018055193999316543, - 0.014001160496263765, - 0.014001160496263765, - 0.014001160496263765, - 0.014001160496263765, - 0.018516544679490227, - 0.018516544679490227, - 0.018516544679490227, - 0.018641953337161492, - 0.018641953337161492, - 0.018641953337161492, - 0.01858119231959184, - 0.01858119231959184, - 0.01858119231959184, - 0.018560895676879834, - 0.018560895676879834, - 0.018560895676879834, - 0.027825927507365122, - 0.027825927507365122, - 0.027690790477208793, - 0.027690790477208793, - 0.014033740997547284, - 0.014033740997547284, - 0.014033740997547284, - 0.014033740997547284, - 0.028556485020089895, - 0.028556485020089895, - 0.018292231000183772, - 0.018292231000183772, - 0.018292231000183772, - 0.03276129499621069, - 0.03276129499621069, - 0.03276129499621069 - ], - [ - 0.114176959003089, - 0.114176959003089, - 0.02001935833444198, - 0.02001935833444198, - 0.02001935833444198, - 0.020075112329019856, - 0.020075112329019856, - 0.020075112329019856, - 0.02003466134192422, - 0.02003466134192422, - 0.02003466134192422, - 0.020026450996131945, - 0.020026450996131945, - 0.020026450996131945, - 0.02973513101460412, - 0.02973513101460412, - 0.030412352993153036, - 0.030412352993153036, - 0.015535941754933447, - 0.015535941754933447, - 0.015535941754933447, - 0.015535941754933447, - 0.02982658799737692, - 0.02982658799737692, - 0.018890631986626733, - 0.018890631986626733, - 0.018890631986626733, - 0.03098562400555238, - 0.03098562400555238, - 0.03098562400555238, - 0.019343592672764014, - 0.019343592672764014, - 0.019343592672764014, - 0.018950106323851895, - 0.018950106323851895, - 0.018950106323851895, - 0.019099269004072994, - 0.019099269004072994, - 0.019099269004072994, - 0.019034251008027542, - 0.019034251008027542, - 0.019034251008027542, - 0.01420391199644655, - 0.01420391199644655, - 0.01420391199644655, - 0.01420391199644655, - 0.01439423524425365, - 0.01439423524425365, - 0.01439423524425365, - 0.01439423524425365, - 0.028566046996274963, - 0.028566046996274963, - 0.01930476234216864, - 0.01930476234216864, - 0.01930476234216864, - 0.019809113660206396, - 0.019809113660206396, - 0.019809113660206396, - 0.014296345761977136, - 0.014296345761977136, - 0.014296345761977136, - 0.014296345761977136, - 0.02867897297255695, - 0.02867897297255695, - 0.019099251677592594, - 0.019099251677592594, - 0.019099251677592594, - 0.019382666000941146, - 0.019382666000941146, - 0.019382666000941146, - 0.02924422750947997, - 0.02924422750947997, - 0.027913359983358532, - 0.027913359983358532, - 0.013784522248897702, - 0.013784522248897702, - 0.013784522248897702, - 0.013784522248897702, - 0.02746082251542248, - 0.02746082251542248, - 0.01840783333561073, - 0.01840783333561073, - 0.01840783333561073, - 0.01856821965581427, - 0.01856821965581427, - 0.01856821965581427, - 0.01835258233283336, - 0.01835258233283336, - 0.01835258233283336, - 0.018347706005442888, - 0.018347706005442888, - 0.018347706005442888, - 0.018484461004845798, - 0.018484461004845798, - 0.018484461004845798, - 0.018302411655895412, - 0.018302411655895412, - 0.018302411655895412, - 0.027679786493536085, - 0.027679786493536085, - 0.027627180505078286, - 0.027627180505078286, - 0.01375247175747063, - 0.01375247175747063, - 0.01375247175747063, - 0.01375247175747063, - 0.0270681754918769, - 0.0270681754918769, - 0.01866779732517898, - 0.01866779732517898, - 0.01866779732517898, - 0.018516544679490227, - 0.018516544679490227, - 0.018516544679490227, - 0.013980599993374199, - 0.013980599993374199, - 0.013980599993374199, - 0.013980599993374199, - 0.027871913509443402, - 0.027871913509443402, - 0.018560129004375387, - 0.018560129004375387, - 0.018560129004375387, - 0.018560815330905218, - 0.018560815330905218, - 0.018560815330905218, - 0.027690300485119224, - 0.027690300485119224, - 0.05595995101612061 - ], - [ - 0.07610034267418087, - 0.07610034267418087, - 0.07610034267418087, - 0.02001753800626223, - 0.02001753800626223, - 0.02001753800626223, - 0.020074322334645938, - 0.020074322334645938, - 0.020074322334645938, - 0.015025673492345959, - 0.015025673492345959, - 0.015025673492345959, - 0.015025673492345959, - 0.03003843649639748, - 0.03003843649639748, - 0.01982440067998444, - 0.01982440067998444, - 0.01982440067998444, - 0.02034523299274345, - 0.02034523299274345, - 0.02034523299274345, - 0.030977007001638412, - 0.030977007001638412, - 0.029805967991705984, - 0.029805967991705984, - 0.014167338755214587, - 0.014167338755214587, - 0.014167338755214587, - 0.014167338755214587, - 0.046478810982080176, - 0.046478810982080176, - 0.01934337633429095, - 0.01934337633429095, - 0.01934337633429095, - 0.0189525830016161, - 0.0189525830016161, - 0.0189525830016161, - 0.014323239010991529, - 0.014323239010991529, - 0.014323239010991529, - 0.014323239010991529, - 0.028550161485327408, - 0.028550161485327408, - 0.018938299675937742, - 0.018938299675937742, - 0.018938299675937742, - 0.019176949999139953, - 0.019176949999139953, - 0.019176949999139953, - 0.028566726978169754, - 0.028566726978169754, - 0.028956993512110785, - 0.028956993512110785, - 0.014857275251415558, - 0.014857275251415558, - 0.014857275251415558, - 0.014857275251415558, - 0.028592451504664496, - 0.028592451504664496, - 0.01912001532036811, - 0.01912001532036811, - 0.01912001532036811, - 0.019098964675019186, - 0.019098964675019186, - 0.019098964675019186, - 0.014537554743583314, - 0.014537554743583314, - 0.014537554743583314, - 0.014537554743583314, - 0.029245732497656718, - 0.029245732497656718, - 0.018609130017769832, - 0.018609130017769832, - 0.018609130017769832, - 0.018378569666917127, - 0.018378569666917127, - 0.018378569666917127, - 0.027461227495223284, - 0.027461227495223284, - 0.013806014991132542, - 0.013806014991132542, - 0.013806014991132542, - 0.013806014991132542, - 0.013926397252362221, - 0.013926397252362221, - 0.013926397252362221, - 0.013926397252362221, - 0.01835247567699601, - 0.01835247567699601, - 0.01835247567699601, - 0.01834764933058371, - 0.01834764933058371, - 0.01834764933058371, - 0.013863673244486563, - 0.013863673244486563, - 0.013863673244486563, - 0.013863673244486563, - 0.027453012502519414, - 0.027453012502519414, - 0.018453627669562895, - 0.018453627669562895, - 0.018453627669562895, - 0.018418410327285528, - 0.018418410327285528, - 0.018418410327285528, - 0.027505588514031842, - 0.027505588514031842, - 0.013533967750845477, - 0.013533967750845477, - 0.013533967750845477, - 0.013533967750845477, - 0.014000577997649089, - 0.014000577997649089, - 0.014000577997649089, - 0.014000577997649089, - 0.018516601334946852, - 0.018516601334946852, - 0.018516601334946852, - 0.018641606671735644, - 0.018641606671735644, - 0.018641606671735644, - 0.013935844239313155, - 0.013935844239313155, - 0.013935844239313155, - 0.013935844239313155, - 0.02784075849922374, - 0.02784075849922374, - 0.018561025344145794, - 0.018561025344145794, - 0.018561025344145794, - 0.01846017032706489, - 0.01846017032706489, - 0.01846017032706489, - 0.02801839599851519, - 0.02801839599851519, - 0.014315253254608251, - 0.014315253254608251, - 0.014315253254608251, - 0.014315253254608251, - 0.013719310751184821, - 0.013719310751184821, - 0.013719310751184821, - 0.013719310751184821, - 0.032736671001960836, - 0.032736671001960836, - 0.032736671001960836, - 0.01810533132326479, - 0.01810533132326479, - 0.01810533132326479, - 0.025817634508712217, - 0.025817634508712217, - 0.017274240672122687, - 0.017274240672122687, - 0.017274240672122687, - 0.012808780491468497, - 0.012808780491468497, - 0.012808780491468497, - 0.012808780491468497, - 0.017103748007987935, - 0.017103748007987935, - 0.017103748007987935, - 0.0260774539783597, - 0.0260774539783597, - 0.012770477012963966, - 0.012770477012963966, - 0.012770477012963966, - 0.012770477012963966, - 0.012633724749321118, - 0.012633724749321118, - 0.012633724749321118, - 0.012633724749321118, - 0.016969308664556593, - 0.016969308664556593, - 0.016969308664556593, - 0.017546184652019292, - 0.017546184652019292, - 0.017546184652019292, - 0.02627176101668738, - 0.02627176101668738, - 0.01677496867099156, - 0.01677496867099156, - 0.01677496867099156, - 0.012476857242290862, - 0.012476857242290862, - 0.012476857242290862, - 0.012476857242290862, - 0.016706993997407455, - 0.016706993997407455, - 0.016706993997407455, - 0.02511487199808471, - 0.02511487199808471, - 0.012620112000149675, - 0.012620112000149675, - 0.012620112000149675, - 0.012620112000149675, - 0.013204801754909568, - 0.013204801754909568, - 0.013204801754909568, - 0.013204801754909568, - 0.016931711327439796, - 0.016931711327439796, - 0.016931711327439796, - 0.025843739014817402, - 0.025843739014817402 - ], - [ - 0.07609820265012483, - 0.07609820265012483, - 0.07609820265012483, - 0.020024441337833803, - 0.020024441337833803, - 0.020024441337833803, - 0.015056459509651177, - 0.015056459509651177, - 0.015056459509651177, - 0.015056459509651177, - 0.03005173648125492, - 0.03005173648125492, - 0.015019418249721639, - 0.015019418249721639, - 0.015019418249721639, - 0.015019418249721639, - 0.019824344334968675, - 0.019824344334968675, - 0.019824344334968675, - 0.020387480326462537, - 0.020387480326462537, - 0.020387480326462537, - 0.020631657680496573, - 0.020631657680496573, - 0.020631657680496573, - 0.01487621849810239, - 0.01487621849810239, - 0.01487621849810239, - 0.01487621849810239, - 0.028335707494989038, - 0.028335707494989038, - 0.023239640504471026, - 0.023239640504471026, - 0.023239640504471026, - 0.023239640504471026, - 0.0193434563310196, - 0.0193434563310196, - 0.0193434563310196, - 0.028431184502551332, - 0.028431184502551332, - 0.014322734248708002, - 0.014322734248708002, - 0.014322734248708002, - 0.014322734248708002, - 0.01903337399320056, - 0.01903337399320056, - 0.01903337399320056, - 0.01893743300267185, - 0.01893743300267185, - 0.01893743300267185, - 0.01917593334413444, - 0.01917593334413444, - 0.01917593334413444, - 0.028568201989401132, - 0.028568201989401132, - 0.01930442900629714, - 0.01930442900629714, - 0.01930442900629714, - 0.014869755497784354, - 0.014869755497784354, - 0.014869755497784354, - 0.014869755497784354, - 0.028589651483343914, - 0.028589651483343914, - 0.019121012010145932, - 0.019121012010145932, - 0.019121012010145932, - 0.01909933132507528, - 0.01909933132507528, - 0.01909933132507528, - 0.0582002800074406 - ], - [ - 0.07609824265819043, - 0.07609824265819043, - 0.07609824265819043, - 0.015011793249868788, - 0.015011793249868788, - 0.015011793249868788, - 0.015011793249868788, - 0.020074732679252822, - 0.020074732679252822, - 0.020074732679252822, - 0.015025845990749076, - 0.015025845990749076, - 0.015025845990749076, - 0.015025845990749076, - 0.030038921511732042, - 0.030038921511732042, - 0.019824267326233286, - 0.019824267326233286, - 0.019824267326233286, - 0.020395867332505684, - 0.020395867332505684, - 0.020395867332505684, - 0.03094582151970826, - 0.03094582151970826, - 0.014877470748615451, - 0.014877470748615451, - 0.014877470748615451, - 0.014877470748615451, - 0.014167653993354179, - 0.014167653993354179, - 0.014167653993354179, - 0.014167653993354179, - 0.030986197331609826, - 0.030986197331609826, - 0.030986197331609826, - 0.01934319967404008, - 0.01934319967404008, - 0.01934319967404008, - 0.014215631992556155, - 0.014215631992556155, - 0.014215631992556155, - 0.014215631992556155, - 0.02864447850151919, - 0.02864447850151919, - 0.01903398767656957, - 0.01903398767656957, - 0.01903398767656957, - 0.018937196330322575, - 0.018937196330322575, - 0.018937196330322575, - 0.028763925016392022, - 0.028763925016392022, - 0.02856709697516635, - 0.02856709697516635, - 0.014478914003120735, - 0.014478914003120735, - 0.014478914003120735, - 0.014478914003120735, - 0.029714685515500605, - 0.029714685515500605, - 0.019061427660441648, - 0.019061427660441648, - 0.019061427660441648, - 0.019120605332621683, - 0.019120605332621683, - 0.019120605332621683, - 0.014324548756121658, - 0.014324548756121658, - 0.014324548756121658, - 0.014324548756121658, - 0.0290751994762104, - 0.0290751994762104, - 0.019497701665386558, - 0.019497701665386558, - 0.019497701665386558, - 0.01860897334214921, - 0.01860897334214921, - 0.01860897334214921, - 0.02756879449589178, - 0.02756879449589178, - 0.02748415298992768, - 0.02748415298992768, - 0.01379515475127846, - 0.01379515475127846, - 0.01379515475127846, - 0.01379515475127846, - 0.02785251452587545, - 0.02785251452587545, - 0.018352062324993312, - 0.018352062324993312, - 0.018352062324993312, - 0.01834822599388038, - 0.01834822599388038, - 0.01834822599388038, - 0.01386378325696569, - 0.01386378325696569, - 0.01386378325696569, - 0.01386378325696569, - 0.02745306250290014, - 0.02745306250290014, - 0.018453344334072124, - 0.018453344334072124, - 0.018453344334072124, - 0.018418603654329974, - 0.018418603654329974, - 0.018418603654329974, - 0.02750637350254692, - 0.02750637350254692, - 0.027067835500929505, - 0.027067835500929505, - 0.014000943003338762, - 0.014000943003338762, - 0.014000943003338762, - 0.014000943003338762, - 0.027774896996561438, - 0.027774896996561438, - 0.01864148332970217, - 0.01864148332970217, - 0.01864148332970217, - 0.018581362344169367, - 0.018581362344169367, - 0.018581362344169367, - 0.013920626748586074, - 0.013920626748586074, - 0.013920626748586074, - 0.013920626748586074, - 0.027841037983307615, - 0.027841037983307615, - 0.018460453681958217, - 0.018460453681958217, - 0.018460453681958217, - 0.018680113988618057, - 0.018680113988618057, - 0.018680113988618057, - 0.028647751518292353, - 0.028647751518292353, - 0.02743947648559697, - 0.02743947648559697, - 0.024545218504499644, - 0.024545218504499644, - 0.024545218504499644, - 0.024545218504499644, - 0.027157786476891488, - 0.027157786476891488, - 0.017211266347051907, - 0.017211266347051907, - 0.017211266347051907, - 0.017274483999547858, - 0.017274483999547858, - 0.017274483999547858, - 0.012808570492779836, - 0.012808570492779836, - 0.012808570492779836, - 0.012808570492779836, - 0.02565537701593712, - 0.02565537701593712, - 0.017431950002598267, - 0.017431950002598267, - 0.017431950002598267, - 0.016987925317759316, - 0.016987925317759316, - 0.016987925317759316, - 0.025259989517508075, - 0.025259989517508075, - 0.012736934004351497, - 0.012736934004351497, - 0.012736934004351497, - 0.012736934004351497, - 0.013151180988643318, - 0.013151180988643318, - 0.013151180988643318, - 0.013151180988643318, - 0.01752863434376195, - 0.01752863434376195, - 0.01752863434376195, - 0.01677370866915832, - 0.01677370866915832, - 0.01677370866915832, - 0.01247714224155061, - 0.01247714224155061, - 0.01247714224155061, - 0.01247714224155061, - 0.025057951017515734, - 0.025057951017515734, - 0.016742911325612415, - 0.016742911325612415, - 0.016742911325612415, - 0.016827172657940537, - 0.016827172657940537, - 0.016827172657940537, - 0.0176063990026402, - 0.0176063990026402, - 0.0176063990026402, - 0.01693138466604675, - 0.01693138466604675, - 0.01693138466604675, - 0.012955810001585633, - 0.012955810001585633, - 0.012955810001585633, - 0.012955810001585633, - 0.016913124340741586, - 0.016913124340741586, - 0.016913124340741586, - 0.015995322338615853, - 0.015995322338615853, - 0.015995322338615853, - 0.012007721743430011, - 0.012007721743430011, - 0.012007721743430011, - 0.012007721743430011, - 0.024051369488006458, - 0.024051369488006458, - 0.015974845349167783, - 0.015974845349167783, - 0.015974845349167783, - 0.015958434999144327, - 0.015958434999144327, - 0.015958434999144327, - 0.015792935659798484, - 0.015792935659798484, - 0.015792935659798484, - 0.01592183733979861, - 0.01592183733979861, - 0.01592183733979861, - 0.011986501252977178, - 0.011986501252977178, - 0.011986501252977178, - 0.011986501252977178, - 0.01585641598406558, - 0.01585641598406558, - 0.01585641598406558, - 0.015924710663966835, - 0.015924710663966835, - 0.015924710663966835, - 0.01634039101190865, - 0.01634039101190865, - 0.01634039101190865 - ], - [ - 0.057074277006904595, - 0.057074277006904595, - 0.057074277006904595, - 0.057074277006904595, - 0.030024631996639073, - 0.030024631996639073, - 0.020074642340963084, - 0.020074642340963084, - 0.020074642340963084, - 0.020034064655192196, - 0.020034064655192196, - 0.020034064655192196, - 0.015019408252555877, - 0.015019408252555877, - 0.015019408252555877, - 0.015019408252555877, - 0.02973640151321888, - 0.02973640151321888, - 0.020345932998073597, - 0.020345932998073597, - 0.020345932998073597, - 0.020652821326317888, - 0.020652821326317888, - 0.020652821326317888, - 0.014902361246640794, - 0.014902361246640794, - 0.014902361246640794, - 0.014902361246640794, - 0.014167511501000263, - 0.014167511501000263, - 0.014167511501000263, - 0.014167511501000263, - 0.04647939599817619, - 0.04647939599817619, - 0.019343009334988892, - 0.019343009334988892, - 0.019343009334988892, - 0.01895378966582939, - 0.01895378966582939, - 0.01895378966582939, - 0.014322384260594845, - 0.014322384260594845, - 0.014322384260594845, - 0.014322384260594845, - 0.02855006148456596, - 0.02855006148456596, - 0.018938185996375978, - 0.018938185996375978, - 0.018938185996375978, - 0.019176096674830962, - 0.019176096674830962, - 0.019176096674830962, - 0.019044518005102873, - 0.019044518005102873, - 0.019044518005102873, - 0.019305008987430483, - 0.019305008987430483, - 0.019305008987430483, - 0.014857510250294581, - 0.014857510250294581, - 0.014857510250294581, - 0.014857510250294581, - 0.0190613410086371, - 0.0190613410086371, - 0.0190613410086371, - 0.019120295338022213, - 0.019120295338022213, - 0.019120295338022213, - 0.0143242962367367, - 0.0143242962367367, - 0.0143242962367367, - 0.0143242962367367, - 0.029075569502310827, - 0.029075569502310827, - 0.019497531349770725, - 0.019497531349770725, - 0.019497531349770725, - 0.018608823651447892, - 0.018608823651447892, - 0.018608823651447892, - 0.018379226346344996, - 0.018379226346344996, - 0.018379226346344996, - 0.018320148325680446, - 0.018320148325680446, - 0.018320148325680446, - 0.01379665250715334, - 0.01379665250715334, - 0.01379665250715334, - 0.01379665250715334, - 0.01856846265339603, - 0.01856846265339603, - 0.01856846265339603, - 0.018352199345827103, - 0.018352199345827103, - 0.018352199345827103, - 0.018347878998611122, - 0.018347878998611122, - 0.018347878998611122, - 0.02772726200055331, - 0.02772726200055331, - 0.013726471239351667, - 0.013726471239351667, - 0.013726471239351667, - 0.013726471239351667, - 0.018453674002860982, - 0.018453674002860982, - 0.018453674002860982, - 0.027627600502455607, - 0.027627600502455607, - 0.013753056759014726, - 0.013753056759014726, - 0.013753056759014726, - 0.013753056759014726, - 0.013533932986319996, - 0.013533932986319996, - 0.013533932986319996, - 0.013533932986319996, - 0.018667823673846822, - 0.018667823673846822, - 0.018667823673846822, - 0.01851649465970695, - 0.01851649465970695, - 0.01851649465970695, - 0.027962180523900315, - 0.027962180523900315, - 0.01858143232918034, - 0.01858143232918034, - 0.01858143232918034, - 0.01392033399315551, - 0.01392033399315551, - 0.01392033399315551, - 0.01392033399315551, - 0.01856105534049372, - 0.01856105534049372, - 0.01856105534049372, - 0.027690295508364215, - 0.027690295508364215, - 0.014009808248374611, - 0.014009808248374611, - 0.014009808248374611, - 0.014009808248374611, - 0.014324050745926797, - 0.014324050745926797, - 0.014324050745926797, - 0.014324050745926797, - 0.018292734341230243, - 0.018292734341230243, - 0.018292734341230243, - 0.03272628099269544, - 0.03272628099269544, - 0.03272628099269544, - 0.027157796488609165, - 0.027157796488609165, - 0.017211413010954857, - 0.017211413010954857, - 0.017211413010954857, - 0.012955822996445931, - 0.012955822996445931, - 0.012955822996445931, - 0.012955822996445931, - 0.017078191003141303, - 0.017078191003141303, - 0.017078191003141303, - 0.02565545149263926, - 0.02565545149263926, - 0.026133759994991124, - 0.026133759994991124, - 0.012745351748890243, - 0.012745351748890243, - 0.012745351748890243, - 0.012745351748890243, - 0.02526378951733932, - 0.02526378951733932, - 0.016981848670790594, - 0.016981848670790594, - 0.016981848670790594, - 0.01753506433063497, - 0.01753506433063497, - 0.01753506433063497, - 0.013146101002348587, - 0.013146101002348587, - 0.013146101002348587, - 0.013146101002348587, - 0.025147862499579787, - 0.025147862499579787, - 0.016644779650960118, - 0.016644779650960118, - 0.016644779650960118, - 0.01670563401421532, - 0.01670563401421532, - 0.01670563401421532, - 0.025114176998613402, - 0.025114176998613402, - 0.025240779505111277, - 0.025240779505111277, - 0.01760628231568262, - 0.01760628231568262, - 0.01760628231568262, - 0.016931691012966137, - 0.016931691012966137, - 0.016931691012966137, - 0.01727279700571671, - 0.01727279700571671, - 0.01727279700571671, - 0.016912257318229724, - 0.016912257318229724, - 0.016912257318229724, - 0.01598840901472916, - 0.01598840901472916, - 0.01598840901472916, - 0.016010235665210832, - 0.016010235665210832, - 0.016010235665210832, - 0.016034339651620638, - 0.016034339651620638, - 0.016034339651620638, - 0.015974988675831508, - 0.015974988675831508, - 0.015974988675831508, - 0.023938142490806058, - 0.023938142490806058, - 0.023689378518611193, - 0.023689378518611193, - 0.01592199399601668, - 0.01592199399601668, - 0.01592199399601668, - 0.01598192499174426, - 0.01598192499174426, - 0.01598192499174426, - 0.01586189299511413, - 0.01586189299511413, - 0.01586189299511413, - 0.015926023673576612, - 0.015926023673576612, - 0.015926023673576612, - 0.016315380674010765, - 0.016315380674010765, - 0.016315380674010765, - 0.017069103002237778, - 0.017069103002237778, - 0.017069103002237778, - 0.015235118994799754, - 0.015235118994799754, - 0.015235118994799754, - 0.015159054659307003, - 0.015159054659307003, - 0.015159054659307003, - 0.022672360995784402, - 0.022672360995784402, - 0.023076677520293742, - 0.023076677520293742 - ], - [ - 0.07599885431894411, - 0.07599885431894411, - 0.07599885431894411, - 0.020025841678337503, - 0.020025841678337503, - 0.020025841678337503, - 0.020075395664510626, - 0.020075395664510626, - 0.020075395664510626, - 0.020034617996619392, - 0.020034617996619392, - 0.020034617996619392, - 0.020026374336642522, - 0.020026374336642522, - 0.020026374336642522, - 0.019823340660271544, - 0.019823340660271544, - 0.019823340660271544, - 0.030416983005125076, - 0.030416983005125076, - 0.03106233850121498, - 0.03106233850121498, - 0.019885292005104322, - 0.019885292005104322, - 0.019885292005104322, - 0.018892501985343795, - 0.018892501985343795, - 0.018892501985343795, - 0.030985270665648084, - 0.030985270665648084, - 0.030985270665648084, - 0.019343586017688114, - 0.019343586017688114, - 0.019343586017688114, - 0.018950182983341318, - 0.018950182983341318, - 0.018950182983341318, - 0.019099209011377145, - 0.019099209011377145, - 0.019099209011377145, - 0.01903421765503784, - 0.01903421765503784, - 0.01903421765503784, - 0.018937779338254284, - 0.018937779338254284, - 0.018937779338254284, - 0.02875587999005802, - 0.02875587999005802, - 0.02856260701082647, - 0.02856260701082647, - 0.019304305334420253, - 0.019304305334420253, - 0.019304305334420253, - 0.019817157338062923, - 0.019817157338062923, - 0.019817157338062923, - 0.019061451001713674, - 0.019061451001713674, - 0.019061451001713674, - 0.019113485332733642, - 0.019113485332733642, - 0.019113485332733642, - 0.019104608334600925, - 0.019104608334600925, - 0.019104608334600925, - 0.02907446399331093, - 0.02907446399331093, - 0.014618368746596389, - 0.014618368746596389, - 0.014618368746596389, - 0.014618368746596389, - 0.018610139998296898, - 0.018610139998296898, - 0.018610139998296898, - 0.02757459500571713, - 0.02757459500571713, - 0.027460306999273598, - 0.027460306999273598, - 0.01380542025435716, - 0.01380542025435716, - 0.01380542025435716, - 0.01380542025435716, - 0.027853768988279626, - 0.027853768988279626, - 0.0183525126776658, - 0.0183525126776658, - 0.0183525126776658, - 0.018347032329378028, - 0.018347032329378028, - 0.018347032329378028, - 0.018484470997160923, - 0.018484470997160923, - 0.018484470997160923, - 0.01830341199335332, - 0.01830341199335332, - 0.01830341199335332, - 0.01845283400810634, - 0.01845283400810634, - 0.01845283400810634, - 0.018417870334815234, - 0.018417870334815234, - 0.018417870334815234, - 0.027498273499077186, - 0.027498273499077186, - 0.027074395504314452, - 0.027074395504314452, - 0.018667700661656756, - 0.018667700661656756, - 0.018667700661656756, - 0.01851662133897965, - 0.01851662133897965, - 0.01851662133897965, - 0.018641199994211394, - 0.018641199994211394, - 0.018641199994211394, - 0.018580482341349125, - 0.018580482341349125, - 0.018580482341349125, - 0.018559868990754087, - 0.018559868990754087, - 0.018559868990754087, - 0.018557828676421195, - 0.018557828676421195, - 0.018557828676421195, - 0.018460286994619917, - 0.018460286994619917, - 0.018460286994619917, - 0.018637193328080077, - 0.018637193328080077, - 0.018637193328080077, - 0.028849135007476434, - 0.028849135007476434, - 0.027445936488220468, - 0.027445936488220468 - ], - [ - 0.07609848600501816, - 0.07609848600501816, - 0.07609848600501816, - 0.02001590799773112, - 0.02001590799773112, - 0.02001590799773112, - 0.020074725985371817, - 0.020074725985371817, - 0.020074725985371817, - 0.015025570755824447, - 0.015025570755824447, - 0.015025570755824447, - 0.015025570755824447, - 0.0200260576675646, - 0.0200260576675646, - 0.0200260576675646, - 0.014868118247250095, - 0.014868118247250095, - 0.014868118247250095, - 0.014868118247250095, - 0.01529539775219746, - 0.01529539775219746, - 0.01529539775219746, - 0.01529539775219746, - 0.0618297120090574 - ], - [ - 0.11415219900663942, - 0.11415219900663942, - 0.020037391669272136, - 0.020037391669272136, - 0.020037391669272136, - 0.015055509502417408, - 0.015055509502417408, - 0.015055509502417408, - 0.015055509502417408, - 0.020034414328013856, - 0.020034414328013856, - 0.020034414328013856, - 0.020025807665660977, - 0.020025807665660977, - 0.020025807665660977, - 0.01982415100792423, - 0.01982415100792423, - 0.01982415100792423, - 0.030516334489220753, - 0.030516334489220753, - 0.015466665499843657, - 0.015466665499843657, - 0.015466665499843657, - 0.015466665499843657, - 0.019884118674478184, - 0.019884118674478184, - 0.019884118674478184, - 0.028335032984614372, - 0.028335032984614372, - 0.023239655507495627, - 0.023239655507495627, - 0.023239655507495627, - 0.023239655507495627, - 0.014507339743431658, - 0.014507339743431658, - 0.014507339743431658, - 0.014507339743431658, - 0.01895076932851225, - 0.01895076932851225, - 0.01895076932851225, - 0.019099789011913042, - 0.019099789011913042, - 0.019099789011913042, - 0.028550306480610743, - 0.028550306480610743, - 0.018938216341969866, - 0.018938216341969866, - 0.018938216341969866, - 0.019193043660682935, - 0.019193043660682935, - 0.019193043660682935, - 0.019044294662307948, - 0.019044294662307948, - 0.019044294662307948, - 0.019304565348041553, - 0.019304565348041553, - 0.019304565348041553, - 0.014856965237413533, - 0.014856965237413533, - 0.014856965237413533, - 0.014856965237413533, - 0.014296558263595216, - 0.014296558263595216, - 0.014296558263595216, - 0.014296558263595216, - 0.01911949533193062, - 0.01911949533193062, - 0.01911949533193062, - 0.019099241665874917, - 0.019099241665874917, - 0.019099241665874917, - 0.029074459482217208, - 0.029074459482217208, - 0.01949675833263124, - 0.01949675833263124, - 0.01949675833263124, - 0.013956615002825856, - 0.013956615002825856, - 0.013956615002825856, - 0.013956615002825856, - 0.018378923006821424, - 0.018378923006821424, - 0.018378923006821424, - 0.027460777491796762, - 0.027460777491796762, - 0.013805887501803227, - 0.013805887501803227, - 0.013805887501803227, - 0.013805887501803227, - 0.013926447005360387, - 0.013926447005360387, - 0.013926447005360387, - 0.013926447005360387, - 0.01835258931775267, - 0.01835258931775267, - 0.01835258931775267, - 0.018347795664643247, - 0.018347795664643247, - 0.018347795664643247, - 0.013863318512449041, - 0.013863318512449041, - 0.013863318512449041, - 0.013863318512449041, - 0.027453502494608983, - 0.027453502494608983, - 0.01845339099721362, - 0.01845339099721362, - 0.01845339099721362, - 0.018418139991505694, - 0.018418139991505694, - 0.018418139991505694, - 0.027505743521032855, - 0.027505743521032855, - 0.027068145980592817, - 0.027068145980592817, - 0.0186672803441373, - 0.0186672803441373, - 0.0186672803441373, - 0.018516397996184725, - 0.018516397996184725, - 0.018516397996184725, - 0.018641243669359635, - 0.018641243669359635, - 0.018641243669359635, - 0.018581482329561066, - 0.018581482329561066, - 0.018581482329561066, - 0.01392028150439728, - 0.01392028150439728, - 0.01392028150439728, - 0.01392028150439728, - 0.027841487986734137, - 0.027841487986734137, - 0.018460020675168682, - 0.018460020675168682, - 0.018460020675168682, - 0.01867730700178072, - 0.01867730700178072, - 0.01867730700178072, - 0.028588780987774953, - 0.028588780987774953, - 0.018283454002812505, - 0.018283454002812505, - 0.018283454002812505, - 0.02455506350088399, - 0.02455506350088399, - 0.02455506350088399, - 0.02455506350088399, - 0.018118704669177532, - 0.018118704669177532, - 0.018118704669177532, - 0.012909814744489267, - 0.012909814744489267, - 0.012909814744489267, - 0.012909814744489267, - 0.012955870508449152, - 0.012955870508449152, - 0.012955870508449152, - 0.012955870508449152, - 0.025617786479415372, - 0.025617786479415372, - 0.01710334767509873, - 0.01710334767509873, - 0.01710334767509873, - 0.01738610933534801, - 0.01738610933534801, - 0.01738610933534801, - 0.025520398980006576, - 0.025520398980006576, - 0.016854186678150047, - 0.016854186678150047, - 0.016854186678150047, - 0.01274280650250148, - 0.01274280650250148, - 0.01274280650250148, - 0.01274280650250148, - 0.02618332498241216, - 0.02618332498241216 - ], - [ - 0.07610312267206609, - 0.07610312267206609, - 0.07610312267206609, - 0.01501510600792244, - 0.01501510600792244, - 0.01501510600792244, - 0.01501510600792244, - 0.020073268989411492, - 0.020073268989411492, - 0.020073268989411492, - 0.020034901332110167, - 0.020034901332110167, - 0.020034901332110167, - 0.01501977325824555, - 0.01501977325824555, - 0.01501977325824555, - 0.01501977325824555, - 0.02973549149464816, - 0.02973549149464816, - 0.06096841796534136 - ] - ], - "generated_texts": [ - " the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed", - " dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit volupt", - " quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog.", - "piciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The", - " The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspic", - "atem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem", - " jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem", - "nis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis", - " error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde omnis iste natus error sit voluptatem. The quick brown fox jumps over", - " voluptatem. The quick brown fox jumps over the lazy dog. Sed ut perspiciatis unde om" - ], - "errors": [ - "", - "", - "", - "", - "", - "", - "", - "", - "", - "" - ] - } - ] - } - ] -} \ No newline at end of file diff --git a/experiments/dsv4_p800_sglang/results/20260708-052659/report.md b/experiments/dsv4_p800_sglang/results/20260708-052659/report.md deleted file mode 100644 index a845a16..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-052659/report.md +++ /dev/null @@ -1,16 +0,0 @@ -# Benchmark Report: dsv4_p800_sglang - -## Metadata - -- **Run ID**: 20260708-052659 -- **Timestamp**: 2026-07-08T05:26:59+00:00 -- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800 -- **Engine/Backend**: sglang-xpu / sglang -- **Hardware**: 8x Kunlun P800 XPU -- **Model**: /data1/models/DeepSeek-V4-Flash-INT8 -- **Git Commit**: 4ef6543 - -## Results - -| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 | -|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| diff --git a/experiments/dsv4_p800_sglang/results/20260708-052659/results.json b/experiments/dsv4_p800_sglang/results/20260708-052659/results.json deleted file mode 100644 index ab11d28..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-052659/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-052659", - "timestamp": "2026-07-08T05:26:59+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "4ef6543", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -} \ No newline at end of file diff --git a/experiments/dsv4_p800_sglang/results/20260708-054332/results.json b/experiments/dsv4_p800_sglang/results/20260708-054332/results.json deleted file mode 100644 index 5c3f4eb..0000000 --- a/experiments/dsv4_p800_sglang/results/20260708-054332/results.json +++ /dev/null @@ -1,20 +0,0 @@ -{ - "metadata": { - "experiment": "dsv4_p800_sglang", - "run_id": "20260708-054332", - "timestamp": "2026-07-08T05:43:32+00:00", - "model": "/data1/models/DeepSeek-V4-Flash-INT8", - "backend": "sglang", - "engine": "sglang-xpu", - "hardware": "8x Kunlun P800 XPU", - "accelerator": "Kunlun P800 XPU", - "chip": "kunlun_p800", - "script": "experiments/dsv4_p800_sglang/run_bench.sh", - "env": "", - "git_commit": "4ef6543", - "git_dirty": "dirty", - "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8" - }, - "config": {}, - "scenarios": [] -}