(APIServer pid=1) INFO 09-16 19:22:27 [api_utils.py:347] 
(APIServer pid=1) INFO 09-16 19:22:27 [api_utils.py:347]        █     █     █▄   ▄█
(APIServer pid=1) INFO 09-16 19:22:27 [api_utils.py:347]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.29.0
(APIServer pid=1) INFO 09-16 19:22:27 [api_utils.py:347]   █▄█▀ █     █     █     █  model   Qwen/Qwen2.5-7B-Instruct
(APIServer pid=1) INFO 09-16 19:22:27 [api_utils.py:347]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=1) INFO 09-16 19:22:27 [api_utils.py:347] 
(APIServer pid=1) INFO 09-16 19:22:27 [api_utils.py:286] non-default args: {'model_tag': 'Qwen/Qwen2.5-7B-Instruct', 'host': '0.0.0.0', 'model': 'Qwen/Qwen2.5-7B-Instruct', 'revision': 'a09a35458c702b33eeacc393d103063234e8bc28', 'max_model_len': 1024, 'served_model_name': ['Qwen/Qwen2.5-7B-Instruct'], 'kv_cache_memory_bytes': 17179869184, 'enable_prefix_caching': False, 'cudagraph_metrics': True, 'max_num_seqs': 256, 'optimization_level': '2'}
(APIServer pid=1) Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
(APIServer pid=1) INFO 09-16 19:22:37 [model.py:684] Resolved architecture: Qwen2ForCausalLM
(APIServer pid=1) INFO 09-16 19:22:37 [model.py:2021] Using max model len 1024
(APIServer pid=1) INFO 09-16 19:22:37 [kernel.py:369] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native'])
(EngineCore pid=132) INFO 09-16 19:22:47 [core.py:123] Initializing a V1 LLM engine (v0.29.0) with config: model='Qwen/Qwen2.5-7B-Instruct', speculative_config=None, tokenizer='Qwen/Qwen2.5-7B-Instruct', skip_tokenizer_init=False, tokenizer_mode=auto, revision=a09a35458c702b33eeacc393d103063234e8bc28, tokenizer_revision=a09a35458c702b33eeacc393d103063234e8bc28, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=1024, 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, per_request_spec_decode_metrics='none', kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=True, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False, jit_monitor_mode='warn', jit_monitor_verbose=False), seed=0, served_model_name=Qwen/Qwen2.5-7B-Instruct, enable_prefix_caching=False, 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::qwen4_exp_compute_ple_ngram_ids', 'vllm::qwen4_exp_ple_short_conv', 'vllm::qwen4_exp_qsa_with_output', 'vllm::linear_attention', 'vllm::qwen_gdn_attention_core', 'vllm::qwen_gdn_attention_core_fused_norm_packed', 'vllm::gdn_attention_core_xpu', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::deepseek_v4_attention', 'vllm::hpc_rope_norm_forward', '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': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': 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, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], '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, 'enable_qk_norm_rope_fusion': False, 'fuse_rope_kvcache_cat_mla': False, 'fuse_act_padding': False, 'fuse_qk_norm_rope_kvcache': False}, 'max_cudagraph_capture_size': 512, '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, enable_cutedsl_warmup=True, enable_jit_warmup=True, enable_bf16x3_router_gemm=False, moe_backend='auto', linear_backend='auto')
(EngineCore pid=132) <frozen importlib._bootstrap_external>:1297: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
(EngineCore pid=132) <frozen importlib._bootstrap_external>:1297: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead.
(EngineCore pid=132) INFO 09-16 19:22:53 [parallel_state.py:1775] world_size=1 rank=0 local_rank=0 distributed_init_method=file:///tmp/vllm_dist_7865cbd5f94d48af8a541ed8de2f628e backend=nccl
(EngineCore pid=132) INFO 09-16 19:22:53 [parallel_state.py:2119] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A, EPLB rank N/A
(EngineCore pid=132) INFO 09-16 19:22:53 [gpu_worker.py:429] Using V2 Model Runner
(EngineCore pid=132) INFO 09-16 19:22:54 [model_runner.py:382] Loading model from scratch...
(EngineCore pid=132) INFO 09-16 19:22:54 [cuda.py:492] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION'].
(EngineCore pid=132) INFO 09-16 19:22:54 [flash_attn.py:897] Using FlashAttention version 2
(EngineCore pid=132) INFO 09-16 19:23:16 [weight_utils.py:526] Time spent downloading weights for Qwen/Qwen2.5-7B-Instruct: 21.733314 seconds
(EngineCore pid=132) INFO 09-16 19:23:16 [weight_utils.py:863] Filesystem type for checkpoints: EXT4. Checkpoint size: 14.19 GiB. Available RAM: 50.52 GiB.
(EngineCore pid=132) INFO 09-16 19:23:16 [weight_utils.py:886] Auto-prefetch is disabled because the filesystem (EXT4) is not a recognized network FS (NFS/Lustre). If you want to force prefetching, start vLLM with --safetensors-load-strategy=prefetch.
(EngineCore pid=132) 
Loading safetensors checkpoint shards:   0% Completed | 0/4 [00:00<?, ?it/s]
(EngineCore pid=132) 
Loading safetensors checkpoint shards:  25% Completed | 1/4 [00:00<00:01,  1.77it/s]
(EngineCore pid=132) 
Loading safetensors checkpoint shards:  50% Completed | 2/4 [00:01<00:01,  1.57it/s]
(EngineCore pid=132) 
Loading safetensors checkpoint shards:  75% Completed | 3/4 [00:01<00:00,  1.50it/s]
(EngineCore pid=132) 
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:02<00:00,  1.54it/s]
(EngineCore pid=132) 
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:02<00:00,  1.55it/s]
(EngineCore pid=132) 
(EngineCore pid=132) INFO 09-16 19:23:19 [default_loader.py:430] Loading weights took 2.71 seconds
(EngineCore pid=132) INFO 09-16 19:23:20 [model_runner.py:404] Model loading took 14.29 GiB memory and 26.309395 seconds
(EngineCore pid=132) INFO 09-16 19:23:20 [topk_topp_sampler.py:62] Using FlashInfer for top-p & top-k sampling.
(EngineCore pid=132) INFO 09-16 19:23:20 [utils.py:306] Using LBNHC KV cache layout.
(EngineCore pid=132) INFO 09-16 19:23:26 [backends.py:1094] Using cache directory: /root/.cache/vllm/torch_compile_cache/fd9ebb7b9a/rank_0_0/backbone for vLLM's torch.compile
(EngineCore pid=132) INFO 09-16 19:23:26 [backends.py:1155] Dynamo bytecode transform time: 5.82 s
(EngineCore pid=132) INFO 09-16 19:23:34 [backends.py:393] Compiling a graph for compile range (1, 2048) takes 7.50 s
(EngineCore pid=132) INFO 09-16 19:23:37 [backends.py:920] collected artifacts: 29 entries, 3 artifacts, 4635169 bytes total
(EngineCore pid=132) INFO 09-16 19:23:37 [decorators.py:719] saved AOT compiled function to /root/.cache/vllm/torch_compile_cache/torch_aot_compile/d30c14480339411d6b55e721379ebd4705912059816be217501f93938fe6c390/rank_0_0/model
(EngineCore pid=132) INFO 09-16 19:23:37 [monitor.py:53] torch.compile took 17.12 s in total
(EngineCore pid=132) INFO 09-16 19:23:38 [monitor.py:81] Initial profiling/warmup run took 0.16 s
(EngineCore pid=132) INFO 09-16 19:23:39 [gpu_worker.py:544] Initial free memory 43.98 GiB, reserved 16.0 GiB memory for KV Cache as specified by kv_cache_memory_bytes config and skipped memory profiling. This does not respect the gpu_memory_utilization config. Only use kv_cache_memory_bytes config when you want manual control of KV cache memory size. If OOM'ed, check the difference of initial free memory between the current run and the previous run where kv_cache_memory_bytes is suggested and update it correspondingly.
(EngineCore pid=132) INFO 09-16 19:23:39 [kv_cache_utils.py:2032] GPU KV cache size: 299,584 tokens, Maximum concurrency for 1,024 tokens per request: 292.56x
(EngineCore pid=132) INFO 09-16 19:23:39 [kernel_warmup.py:124] JIT kernel warmup starting.
(EngineCore pid=132) INFO 09-16 19:23:39 [kernel_warmup.py:134] JIT kernel warmup finished in 0.00s.
(EngineCore pid=132) 
Capturing CUDA graphs (PIECEWISE):   0%|          | 0/51 [00:00<?, ?it/s]
Capturing CUDA graphs (PIECEWISE):   4%|▍         | 2/51 [00:00<00:04, 10.99it/s]
Capturing CUDA graphs (PIECEWISE):   8%|▊         | 4/51 [00:00<00:04, 11.23it/s]
Capturing CUDA graphs (PIECEWISE):  12%|█▏        | 6/51 [00:00<00:03, 11.30it/s]
Capturing CUDA graphs (PIECEWISE):  16%|█▌        | 8/51 [00:00<00:03, 11.48it/s]
Capturing CUDA graphs (PIECEWISE):  20%|█▉        | 10/51 [00:00<00:03, 12.13it/s]
Capturing CUDA graphs (PIECEWISE):  24%|██▎       | 12/51 [00:00<00:03, 12.58it/s]
Capturing CUDA graphs (PIECEWISE):  27%|██▋       | 14/51 [00:01<00:02, 12.87it/s]
Capturing CUDA graphs (PIECEWISE):  31%|███▏      | 16/51 [00:01<00:02, 13.17it/s]
Capturing CUDA graphs (PIECEWISE):  35%|███▌      | 18/51 [00:01<00:02, 13.88it/s]
Capturing CUDA graphs (PIECEWISE):  39%|███▉      | 20/51 [00:01<00:02, 14.81it/s]
Capturing CUDA graphs (PIECEWISE):  43%|████▎     | 22/51 [00:01<00:01, 15.62it/s]
Capturing CUDA graphs (PIECEWISE):  47%|████▋     | 24/51 [00:01<00:01, 16.14it/s]
Capturing CUDA graphs (PIECEWISE):  51%|█████     | 26/51 [00:01<00:01, 16.51it/s]
Capturing CUDA graphs (PIECEWISE):  55%|█████▍    | 28/51 [00:01<00:01, 16.89it/s]
Capturing CUDA graphs (PIECEWISE):  59%|█████▉    | 30/51 [00:02<00:01, 17.21it/s]
Capturing CUDA graphs (PIECEWISE):  63%|██████▎   | 32/51 [00:02<00:01, 17.54it/s]
Capturing CUDA graphs (PIECEWISE):  67%|██████▋   | 34/51 [00:02<00:00, 17.94it/s]
Capturing CUDA graphs (PIECEWISE):  71%|███████   | 36/51 [00:02<00:00, 18.11it/s]
Capturing CUDA graphs (PIECEWISE):  75%|███████▍  | 38/51 [00:02<00:00, 17.56it/s]
Capturing CUDA graphs (PIECEWISE):  78%|███████▊  | 40/51 [00:02<00:00, 18.00it/s]
Capturing CUDA graphs (PIECEWISE):  82%|████████▏ | 42/51 [00:02<00:00, 18.40it/s]
Capturing CUDA graphs (PIECEWISE):  86%|████████▋ | 44/51 [00:02<00:00, 18.79it/s]
Capturing CUDA graphs (PIECEWISE):  90%|█████████ | 46/51 [00:02<00:00, 19.08it/s]
Capturing CUDA graphs (PIECEWISE):  96%|█████████▌| 49/51 [00:03<00:00, 19.73it/s]
Capturing CUDA graphs (PIECEWISE): 100%|██████████| 51/51 [00:03<00:00, 19.47it/s]
Capturing CUDA graphs (PIECEWISE): 100%|██████████| 51/51 [00:03<00:00, 15.93it/s]
(EngineCore pid=132) 
Capturing CUDA graphs (FULL):   0%|          | 0/35 [00:00<?, ?it/s]
Capturing CUDA graphs (FULL):   9%|▊         | 3/35 [00:00<00:01, 22.83it/s]
Capturing CUDA graphs (FULL):  17%|█▋        | 6/35 [00:00<00:01, 22.94it/s]
Capturing CUDA graphs (FULL):  26%|██▌       | 9/35 [00:00<00:01, 23.25it/s]
Capturing CUDA graphs (FULL):  34%|███▍      | 12/35 [00:00<00:00, 23.47it/s]
Capturing CUDA graphs (FULL):  43%|████▎     | 15/35 [00:00<00:00, 23.77it/s]
Capturing CUDA graphs (FULL):  51%|█████▏    | 18/35 [00:00<00:00, 24.30it/s]
Capturing CUDA graphs (FULL):  60%|██████    | 21/35 [00:00<00:00, 24.77it/s]
Capturing CUDA graphs (FULL):  69%|██████▊   | 24/35 [00:00<00:00, 25.06it/s]
Capturing CUDA graphs (FULL):  77%|███████▋  | 27/35 [00:01<00:00, 24.95it/s]
Capturing CUDA graphs (FULL):  86%|████████▌ | 30/35 [00:01<00:00, 25.43it/s]
Capturing CUDA graphs (FULL):  97%|█████████▋| 34/35 [00:01<00:00, 27.03it/s]
Capturing CUDA graphs (FULL): 100%|██████████| 35/35 [00:01<00:00, 25.21it/s]
(EngineCore pid=132) INFO 09-16 19:23:44 [model_runner.py:960] Graph capturing finished in 5 secs, took 0.52 GiB
(EngineCore pid=132) INFO 09-16 19:23:48 [jit_monitor.py:85] Kernel JIT monitor activated; monitored JIT compilations during inference will use mode=warn.
(EngineCore pid=132) INFO 09-16 19:23:49 [torch_utils.py:277] Reducing Torch threads from 28 to 1 for serving. Set OMP_NUM_THREADS in the external environment to override.
(EngineCore pid=132) INFO 09-16 19:23:49 [core.py:361] init engine (profile, create kv cache, warmup model) took 29.24 s (compilation: 17.12 s)
(EngineCore pid=132) INFO 09-16 19:23:50 [kernel.py:369] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native'])
(APIServer pid=1) INFO 09-16 19:23:50 [entry.py:135] Supported tasks: ['generate']
(APIServer pid=1) WARNING 09-16 19:23:50 [__init__.py:44] SECURITY WARNING: Development endpoints are enabled! This should NOT be used in production!
(APIServer pid=1) INFO 09-16 19:23:50 [hf.py:547] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this.
(APIServer pid=1) WARNING 09-16 19:23:50 [model.py:1759] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'repetition_penalty': 1.05, 'temperature': 0.7, 'top_k': 20, 'top_p': 0.8}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`.
(APIServer pid=1) INFO 09-16 19:23:50 [entry.py:139] Starting vLLM server on http://0.0.0.0:8000
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:61] Available routes are:
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /openapi.json, Methods: GET, HEAD
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /docs, Methods: GET, HEAD
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /docs/oauth2-redirect, Methods: GET, HEAD
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /redoc, Methods: GET, HEAD
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /load, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /version, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /health, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /metrics, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /tokenize, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /detokenize, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/models, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /ping, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /ping, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /invocations, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /reset_prefix_cache, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /reset_mm_cache, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /reset_encoder_cache, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /pause, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /resume, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /abort_requests, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /is_paused, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /init_weight_transfer_engine, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /start_weight_update, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /start_draft_weight_update, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /update_weights, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /finish_weight_update, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /update_weight_version, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /weight_info, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /get_world_size, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /collective_rpc, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /server_info, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /sleep, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /wake_up, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /is_sleeping, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/chat/completions, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/chat/completions/batch, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/responses, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/responses/{response_id}, Methods: GET
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/responses/{response_id}/cancel, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/completions, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/messages, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/messages/count_tokens, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /generative_scoring, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /scale_elastic_ep, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /is_scaling_elastic_ep, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/chat/completions/render, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/messages/render, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/completions/render, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/chat/completions/derender, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /v1/completions/derender, Methods: POST
(APIServer pid=1) INFO 09-16 19:23:50 [launcher.py:70] Route: /inference/v1/generate, Methods: POST
(APIServer pid=1) INFO:     Started server process [1]
(APIServer pid=1) INFO:     Waiting for application startup.
(APIServer pid=1) INFO:     Application startup complete.
(APIServer pid=1) INFO:     172.17.0.1:41182 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO:     172.17.0.1:41192 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO:     172.17.0.1:41200 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO:     172.17.0.1:41206 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO:     172.17.0.1:41210 - "GET /version HTTP/1.1" 200 OK
(APIServer pid=1) INFO:     172.17.0.1:41222 - "GET /metrics HTTP/1.1" 200 OK
(APIServer pid=1) INFO:     172.17.0.1:41236 - "GET /metrics HTTP/1.1" 200 OK
(APIServer pid=1) INFO:     172.17.0.1:41244 - "GET /server_info?config_format=json HTTP/1.1" 200 OK
(APIServer pid=1) INFO:     172.17.0.1:41254 - "GET /v1/models HTTP/1.1" 200 OK