gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
9b3a2eab80faa79bf06596d3559df5a3e216ac39
aituner/runs/opprof-phase6/phase6/cells/tp1_mns8/server.log
Gahow Wang d5b276180d Add OpProf campaign: protocols, results, patches, run evidence (P0-P6) 
Workload-conditioned operator profiling on patched vLLM 0.24.0 +
Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64
raggedness, 8-45% token-efficiency loss vs rectangular controls);
mechanism decomposition kills the padding narrative and finds the
arrival-uniformization artifact (-12.9%); cross-version churn surface
shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held.
Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer
sidecars and metrics are tracked.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-13 11:06:10 +08:00

328 lines
40 KiB
Plaintext
Raw Blame History

(APIServer pid=2638186) INFO 07-12 14:50:41 [api_utils.py:339]
(APIServer pid=2638186) INFO 07-12 14:50:41 [api_utils.py:339] █ █ █▄ ▄█
(APIServer pid=2638186) INFO 07-12 14:50:41 [api_utils.py:339] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.24.1.dev3+g668cfb7e2
(APIServer pid=2638186) INFO 07-12 14:50:41 [api_utils.py:339] █▄█▀ █ █ █ █ model /home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B
(APIServer pid=2638186) INFO 07-12 14:50:41 [api_utils.py:339] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀
(APIServer pid=2638186) INFO 07-12 14:50:41 [api_utils.py:339]
(APIServer pid=2638186) INFO 07-12 14:50:41 [api_utils.py:273] non-default args: {'model_tag': '/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B', 'host': '127.0.0.1', 'port': 8500, 'model': '/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B', 'served_model_name': ['qwen3-30b-a3b-community'], 'max_num_batched_tokens': 8192, 'max_num_seqs': 8, 'shutdown_timeout': 120}
(APIServer pid=2638186) INFO 07-12 14:50:52 [model.py:598] Resolved architecture: Qwen3MoeForCausalLM
(APIServer pid=2638186) INFO 07-12 14:50:52 [model.py:1725] Using max model len 40960
(APIServer pid=2638186) INFO 07-12 14:50:52 [scheduler.py:252] Chunked prefill is enabled with max_num_batched_tokens=8192.
(APIServer pid=2638186) INFO 07-12 14:50:52 [vllm.py:1006] Asynchronous scheduling is enabled.
(APIServer pid=2638186) INFO 07-12 14:50:52 [kernel.py:276] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native'])
(EngineCore pid=2638884) INFO 07-12 14:51:03 [core.py:114] Initializing a V1 LLM engine (v0.24.1.dev3+g668cfb7e2) with config: model='/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B', speculative_config=None, tokenizer='/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=40960, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=False, quantization=None, quantization_config=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False, jit_monitor_verbose=False), seed=0, served_model_name=qwen3-30b-a3b-community, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none'], 'ir_enable_torch_wrap': True, 'splitting_ops': ['vllm::unified_attention_with_output', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::qwen_gdn_attention_core', 'vllm::gdn_attention_core_xpu', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::deepseek_v4_attention', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_vision_items_per_batch': 0, 'encoder_cudagraph_max_frames_per_batch': None, 'compile_sizes': [], 'compile_ranges_endpoints': [8192], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'size_asserts': False, 'alignment_asserts': False, 'scalar_asserts': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_rope_kvcache_cat_mla': False, 'fuse_act_padding': False}, 'max_cudagraph_capture_size': 16, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}, kernel_config=KernelConfig(ir_op_priority=IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native']), enable_flashinfer_autotune=True, moe_backend='auto', linear_backend='auto')
(EngineCore pid=2638884) INFO 07-12 14:51:06 [parallel_state.py:1588] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://172.27.132.244:48769 backend=nccl
(EngineCore pid=2638884) INFO 07-12 14:51:06 [parallel_state.py:1923] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank 0, EPLB rank N/A
(EngineCore pid=2638884) INFO 07-12 14:51:07 [topk_topp_sampler.py:55] Using FlashInfer for top-p & top-k sampling.
(EngineCore pid=2638884) INFO 07-12 14:51:07 [gpu_model_runner.py:5164] Starting to load model /home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B...
(EngineCore pid=2638884) INFO 07-12 14:51:07 [cuda.py:480] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION'].
(EngineCore pid=2638884) INFO 07-12 14:51:07 [flash_attn.py:670] Using FlashAttention version 3
(EngineCore pid=2638884) INFO 07-12 14:51:07 [unquantized.py:247] Using TRITON Unquantized MoE backend out of potential backends: ['TRITON', 'BATCHED_TRITON', 'FlashInfer TRTLLM', 'FlashInfer CUTLASS'].
(EngineCore pid=2638884) INFO 07-12 14:51:08 [weight_utils.py:849] Filesystem type for checkpoints: FUSE.ALIYUN-ALINAS-EFC. Checkpoint size: 56.87 GiB. Available RAM: 1283.36 GiB.
(EngineCore pid=2638884) INFO 07-12 14:51:08 [weight_utils.py:872] Auto-prefetch is disabled because the filesystem (FUSE.ALIYUN-ALINAS-EFC) is not a recognized network FS (NFS/Lustre). If you want to force prefetching, start vLLM with --safetensors-load-strategy=prefetch.
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 0% Completed | 0/16 [00:00<?, ?it/s]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 6% Completed | 1/16 [00:01<00:15, 1.06s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 12% Completed | 2/16 [00:02<00:14, 1.07s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 19% Completed | 3/16 [00:03<00:13, 1.06s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 25% Completed | 4/16 [00:04<00:13, 1.10s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 31% Completed | 5/16 [00:05<00:11, 1.07s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 38% Completed | 6/16 [00:06<00:10, 1.09s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 44% Completed | 7/16 [00:07<00:09, 1.11s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 50% Completed | 8/16 [00:08<00:08, 1.10s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 56% Completed | 9/16 [00:09<00:07, 1.08s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 62% Completed | 10/16 [00:10<00:06, 1.07s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 69% Completed | 11/16 [00:11<00:05, 1.06s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 75% Completed | 12/16 [00:12<00:04, 1.04s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 81% Completed | 13/16 [00:13<00:03, 1.06s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 88% Completed | 14/16 [00:15<00:02, 1.09s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 94% Completed | 15/16 [00:16<00:01, 1.09s/it]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 100% Completed | 16/16 [00:16<00:00, 1.18it/s]
(EngineCore pid=2638884)
Loading safetensors checkpoint shards: 100% Completed | 16/16 [00:16<00:00, 1.03s/it]
(EngineCore pid=2638884)
(EngineCore pid=2638884) INFO 07-12 14:51:25 [default_loader.py:430] Loading weights took 16.49 seconds
(EngineCore pid=2638884) INFO 07-12 14:51:25 [unquantized.py:312] Using MoEPrepareAndFinalizeNoDPEPModular
(EngineCore pid=2638884) INFO 07-12 14:51:25 [gpu_model_runner.py:5259] Model loading took 56.88 GiB memory and 17.240093 seconds
(EngineCore pid=2638884) INFO 07-12 14:51:35 [backends.py:1089] Using cache directory: /home/admin/cpfs/wjh/.cache/vllm/torch_compile_cache/b95eb69a3d/rank_0_0/backbone for vLLM's torch.compile
(EngineCore pid=2638884) INFO 07-12 14:51:35 [backends.py:1148] Dynamo bytecode transform time: 9.16 s
(EngineCore pid=2638884) INFO 07-12 14:51:50 [backends.py:378] Cache the graph of compile range (1, 8192) for later use
(EngineCore pid=2638884) INFO 07-12 14:51:58 [backends.py:393] Compiling a graph for compile range (1, 8192) takes 23.00 s
(EngineCore pid=2638884) INFO 07-12 14:52:03 [decorators.py:708] saved AOT compiled function to /home/admin/cpfs/wjh/.cache/vllm/torch_compile_cache/torch_aot_compile/802e9eed10a34f87d59e9a1acfc3b883a63a5eaeb40312e4832ac27dfbf354e5/rank_0_0/model
(EngineCore pid=2638884) INFO 07-12 14:52:03 [monitor.py:53] torch.compile took 37.35 s in total
(EngineCore pid=2638884) INFO 07-12 14:52:03 [fused_moe.py:1058] Using configuration from /home/admin/cpfs/wjh/opprof-phase2-dash0-20260711/vllm-v0.24.0/vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json for MoE layer.
(EngineCore pid=2638884) INFO 07-12 14:52:05 [monitor.py:81] Initial profiling/warmup run took 2.19 s
(EngineCore pid=2638884) INFO 07-12 14:52:12 [gpu_model_runner.py:6487] Profiling CUDA graph memory: PIECEWISE=5 (largest=16), FULL=4 (largest=8)
(EngineCore pid=2638884) INFO 07-12 14:52:17 [gpu_model_runner.py:6592] Estimated CUDA graph memory: 0.07 GiB total
(EngineCore pid=2638884) INFO 07-12 14:52:18 [gpu_worker.py:508] Available KV cache memory: 29.44 GiB
(EngineCore pid=2638884) INFO 07-12 14:52:18 [gpu_worker.py:523] CUDA graph memory profiling is enabled (default since v0.21.0). The current --gpu-memory-utilization=0.9200 is equivalent to --gpu-memory-utilization=0.9193 without CUDA graph memory profiling. To maintain the same effective KV cache size as before, increase --gpu-memory-utilization to 0.9207. To disable, set VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0.
(EngineCore pid=2638884) INFO 07-12 14:52:18 [kv_cache_utils.py:2146] GPU KV cache size: 321,600 tokens
(EngineCore pid=2638884) INFO 07-12 14:52:18 [kv_cache_utils.py:2147] Maximum concurrency for 40,960 tokens per request: 7.85x
(EngineCore pid=2638884) INFO 07-12 14:52:18 [deep_gemm.py:175] deep_gemm not found in site-packages, trying vendored vllm.third_party.deep_gemm
(EngineCore pid=2638884) INFO 07-12 14:52:18 [deep_gemm.py:202] DeepGEMM PDL enabled on vllm.third_party.deep_gemm.
(EngineCore pid=2638884) 2026-07-12 14:52:18,390 - INFO - autotuner.py:622 - flashinfer.jit: [Autotuner]: Autotuning process starts ...
(EngineCore pid=2638884) 2026-07-12 14:52:18,429 - INFO - autotuner.py:641 - flashinfer.jit: [Autotuner]: Autotuning process ends
(EngineCore pid=2638884)
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 0%| | 0/5 [00:00<?, ?it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 40%|████ | 2/5 [00:00<00:00, 10.98it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 80%|████████ | 4/5 [00:01<00:00, 2.57it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|██████████| 5/5 [00:02<00:00, 1.77it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|██████████| 5/5 [00:02<00:00, 2.12it/s]
(EngineCore pid=2638884)
Capturing CUDA graphs (decode, FULL): 0%| | 0/4 [00:00<?, ?it/s]
Capturing CUDA graphs (decode, FULL): 50%|█████ | 2/4 [00:00<00:00, 11.61it/s]
Capturing CUDA graphs (decode, FULL): 100%|██████████| 4/4 [00:00<00:00, 11.88it/s]
Capturing CUDA graphs (decode, FULL): 100%|██████████| 4/4 [00:00<00:00, 11.84it/s]
(EngineCore pid=2638884) INFO 07-12 14:52:21 [gpu_model_runner.py:6660] Graph capturing finished in 3 secs, took 0.08 GiB
(EngineCore pid=2638884) INFO 07-12 14:52:21 [gpu_worker.py:667] CUDA graph pool memory: 0.08 GiB (actual), 0.07 GiB (estimated), difference: 0.01 GiB (12.2%).
(EngineCore pid=2638884) INFO 07-12 14:52:21 [jit_monitor.py:60] Kernel JIT monitor activated — Triton JIT compilations during inference will be logged as warnings.
(EngineCore pid=2638884) INFO 07-12 14:52:22 [core.py:337] init engine (profile, create kv cache, warmup model) took 56.63 s (compilation: 37.35 s)
(EngineCore pid=2638884) INFO 07-12 14:52:22 [scheduler.py:282] OpProf telemetry enabled: /home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp1_mns8/opprof/opprof-v1-dp0-pid2638884-1783867942846550713.jsonl
(EngineCore pid=2638884) INFO 07-12 14:52:22 [vllm.py:1006] Asynchronous scheduling is enabled.
(EngineCore pid=2638884) INFO 07-12 14:52:22 [kernel.py:276] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native'])
(APIServer pid=2638186) INFO 07-12 14:52:22 [api_server.py:577] Supported tasks: ['generate']
(APIServer pid=2638186) WARNING 07-12 14:52:23 [model.py:1477] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'temperature': 0.6, 'top_k': 20, 'top_p': 0.95}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`.
(APIServer pid=2638186) INFO 07-12 14:52:23 [hf.py:548] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this.
(APIServer pid=2638186) INFO 07-12 14:52:23 [api_server.py:581] Starting vLLM server on http://127.0.0.1:8500
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:37] Available routes are:
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /openapi.json, Methods: GET, HEAD
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /docs, Methods: GET, HEAD
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: GET, HEAD
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /redoc, Methods: GET, HEAD
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /load, Methods: GET
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /version, Methods: GET
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /health, Methods: GET
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /metrics, Methods: GET
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /tokenize, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /detokenize, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/models, Methods: GET
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /ping, Methods: GET
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /ping, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /invocations, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/chat/completions, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/chat/completions/batch, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/responses, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/responses/{response_id}, Methods: GET
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/responses/{response_id}/cancel, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/completions, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/messages, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/messages/count_tokens, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /generative_scoring, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /inference/v1/generate, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /scale_elastic_ep, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /is_scaling_elastic_ep, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/chat/completions/render, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/completions/render, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/chat/completions/derender, Methods: POST
(APIServer pid=2638186) INFO 07-12 14:52:23 [launcher.py:46] Route: /v1/completions/derender, Methods: POST
(APIServer pid=2638186) INFO: Started server process [2638186]
(APIServer pid=2638186) INFO: Waiting for application startup.
(APIServer pid=2638186) INFO: Application startup complete.
(APIServer pid=2638186) INFO: 127.0.0.1:50438 - "GET /v1/models HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:50454 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:50460 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(EngineCore pid=2638884) WARNING 07-12 14:52:29 [jit_monitor.py:106] Triton kernel JIT compilation during inference: _compute_slot_mapping_kernel. This causes a latency spike; consider extending warmup to cover this shape/config.
(APIServer pid=2638186) INFO: 127.0.0.1:50472 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51342 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51348 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51352 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(EngineCore pid=2638884) WARNING 07-12 14:52:31 [jit_monitor.py:106] Triton kernel JIT compilation during inference: fused_moe_kernel. This causes a latency spike; consider extending warmup to cover this shape/config.
(APIServer pid=2638186) INFO: 127.0.0.1:51354 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51370 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51374 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:52:33 [loggers.py:273] Engine 000: Avg prompt throughput: 1338.9 tokens/s, Avg generation throughput: 0.9 tokens/s, Running: 8 reqs, Waiting: 1 reqs, GPU KV cache usage: 7.1%, Prefix cache hit rate: 4.2%
(APIServer pid=2638186) INFO: 127.0.0.1:51380 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51394 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51408 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51418 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51432 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51438 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51450 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:52:43 [loggers.py:273] Engine 000: Avg prompt throughput: 2863.4 tokens/s, Avg generation throughput: 203.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 5.0%
(APIServer pid=2638186) INFO: 127.0.0.1:34496 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:34512 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:34518 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:34522 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:34526 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:34542 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:34556 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:34572 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51252 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51258 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51274 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51280 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:52:53 [loggers.py:273] Engine 000: Avg prompt throughput: 14.3 tokens/s, Avg generation throughput: 153.6 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 47.0%
(APIServer pid=2638186) INFO: 127.0.0.1:51288 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51294 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51310 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51322 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51332 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51344 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51346 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51354 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51362 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51364 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51366 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51372 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51384 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51398 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51400 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51410 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51412 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51422 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:51438 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42366 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42382 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42384 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42396 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42406 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42414 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42424 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42436 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:53:03 [loggers.py:273] Engine 000: Avg prompt throughput: 3326.2 tokens/s, Avg generation throughput: 188.1 tokens/s, Running: 7 reqs, Waiting: 8 reqs, GPU KV cache usage: 7.0%, Prefix cache hit rate: 39.8%
(APIServer pid=2638186) INFO: 127.0.0.1:42448 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42462 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42476 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42478 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42482 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42488 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42496 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42506 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:42522 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:53:13 [loggers.py:273] Engine 000: Avg prompt throughput: 3070.5 tokens/s, Avg generation throughput: 160.1 tokens/s, Running: 7 reqs, Waiting: 3 reqs, GPU KV cache usage: 4.9%, Prefix cache hit rate: 34.1%
(APIServer pid=2638186) INFO 07-12 14:53:23 [loggers.py:273] Engine 000: Avg prompt throughput: 674.1 tokens/s, Avg generation throughput: 112.6 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 33.4%
(APIServer pid=2638186) INFO 07-12 14:53:33 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 33.4%
(APIServer pid=2638186) INFO: 127.0.0.1:35688 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35694 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35708 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35710 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35714 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35722 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35724 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35736 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35738 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35750 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35762 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35640 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35646 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35654 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35656 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35670 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35674 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35690 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:54:03 [loggers.py:273] Engine 000: Avg prompt throughput: 20.3 tokens/s, Avg generation throughput: 219.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.5%, Prefix cache hit rate: 47.8%
(APIServer pid=2638186) INFO: 127.0.0.1:35706 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35722 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35726 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35730 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35732 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35734 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35736 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35738 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35744 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35758 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35764 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35780 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35786 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35790 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35806 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35822 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:35836 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59704 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59720 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59730 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59738 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59744 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59750 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59758 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:54:13 [loggers.py:273] Engine 000: Avg prompt throughput: 21.0 tokens/s, Avg generation throughput: 311.2 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.9%, Prefix cache hit rate: 58.8%
(APIServer pid=2638186) INFO: 127.0.0.1:59770 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59776 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59788 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59790 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59800 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59810 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:59822 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36438 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36440 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36444 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36448 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:54:23 [loggers.py:273] Engine 000: Avg prompt throughput: 1393.0 tokens/s, Avg generation throughput: 110.0 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.1%, Prefix cache hit rate: 56.5%
(APIServer pid=2638186) INFO: 127.0.0.1:36450 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36452 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36462 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36466 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36478 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36480 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36494 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36506 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36518 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36534 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36536 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36546 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36548 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:36558 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58018 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58032 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58042 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58048 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58052 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58060 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58068 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:54:33 [loggers.py:273] Engine 000: Avg prompt throughput: 5941.7 tokens/s, Avg generation throughput: 269.5 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.8%, Prefix cache hit rate: 48.4%
(APIServer pid=2638186) INFO: 127.0.0.1:58076 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58086 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58090 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58098 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58102 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58114 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58122 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58138 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58150 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58158 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58166 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58176 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58182 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58186 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58202 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58206 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58222 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:58228 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47530 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47544 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47550 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47554 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47564 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47580 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47586 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47592 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:54:43 [loggers.py:273] Engine 000: Avg prompt throughput: 8113.3 tokens/s, Avg generation throughput: 349.9 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.1%, Prefix cache hit rate: 41.3%
(APIServer pid=2638186) INFO: 127.0.0.1:47602 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47612 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47616 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47622 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47628 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47636 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47652 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47664 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47680 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47692 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:47708 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:39082 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:39090 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:39096 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:39098 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:39114 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:39126 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:39136 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:39150 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO 07-12 14:54:53 [loggers.py:273] Engine 000: Avg prompt throughput: 6378.8 tokens/s, Avg generation throughput: 231.0 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.8%, Prefix cache hit rate: 36.6%
(APIServer pid=2638186) INFO: 127.0.0.1:39152 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=2638186) INFO: 127.0.0.1:39164 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(EngineCore pid=2638884) INFO 07-12 14:54:56 [core.py:1214] [shutdown] EngineCore: trigger received signal=SIGTERM
(APIServer pid=2638186) INFO 07-12 14:54:56 [launcher.py:100] [shutdown] API server: shutdown triggered
(APIServer pid=2638186) INFO 07-12 14:54:56 [launcher.py:116] [shutdown] API server: stopping engine client mode=drain timeout=120s
(EngineCore pid=2638884) INFO 07-12 14:54:56 [core.py:1333] [shutdown] EngineCore: start mode=drain timeout=120s
(EngineCore pid=2638884) INFO 07-12 14:54:56 [core.py:1364] [shutdown] EngineCore: request processing complete; starting resource teardown
(EngineCore pid=2638884) INFO 07-12 14:54:56 [core.py:1227] [shutdown] EngineCore: exiting busy loop
(APIServer pid=2638186) INFO 07-12 14:54:56 [core_client.py:655] [shutdown] MPClient: start timeout=120s
(APIServer pid=2638186) INFO 07-12 14:54:56 [core_client.py:657] [shutdown] MPClient: stopping engine manager
(APIServer pid=2638186) INFO: Shutting down
(APIServer pid=2638186) INFO: Waiting for application shutdown.
(APIServer pid=2638186) INFO: Application shutdown complete.
(APIServer pid=2638186) INFO: Finished server process [2638186]
(APIServer pid=2638186) INFO 07-12 14:54:57 [core_client.py:659] [shutdown] MPClient: engine manager stopped
(APIServer pid=2638186) INFO 07-12 14:54:57 [core_client.py:660] [shutdown] MPClient: cleaning up background resources
(APIServer pid=2638186) INFO 07-12 14:54:57 [core_client.py:662] [shutdown] MPClient: complete
/usr/lib/python3.12/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
Reference in New Issue View Git Blame Copy Permalink