| (APIServer pid=1128487) INFO 07-23 22:02:32 [api_utils.py:339]
|
| (APIServer pid=1128487) INFO 07-23 22:02:32 [api_utils.py:339] █ █ █▄ ▄█
|
| (APIServer pid=1128487) INFO 07-23 22:02:32 [api_utils.py:339] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.25.0
|
| (APIServer pid=1128487) INFO 07-23 22:02:32 [api_utils.py:339] █▄█▀ █ █ █ █ model outputs/qwen35_pruned_keep25
|
| (APIServer pid=1128487) INFO 07-23 22:02:32 [api_utils.py:339] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀
|
| (APIServer pid=1128487) INFO 07-23 22:02:32 [api_utils.py:339] |
| (APIServer pid=1128487) INFO 07-23 22:02:32 [api_utils.py:273] non-default args: {'model_tag': 'outputs/qwen35_pruned_keep25', 'default_chat_template_kwargs': {'enable_thinking': False}, 'host': '127.0.0.1', 'port': 8399, 'model': 'outputs/qwen35_pruned_keep25', 'max_model_len': 4096, 'enforce_eager': True, 'served_model_name': ['student'], 'pipeline_parallel_size': 2, 'gpu_memory_utilization': 0.9} |
| (APIServer pid=1128487) INFO 07-23 22:02:32 [model.py:619] Resolved architecture: PrunedQwen3_5MoeForCausalLM |
| (APIServer pid=1128487) INFO 07-23 22:02:32 [model.py:1776] Using max model len 4096 |
| (APIServer pid=1128487) INFO 07-23 22:02:32 [vllm.py:1042] Asynchronous scheduling is enabled. |
| (APIServer pid=1128487) WARNING 07-23 22:02:32 [vllm.py:1096] Enforce eager set, disabling torch.compile and CUDAGraphs. This is equivalent to setting -cc.mode=none -cc.cudagraph_mode=none |
| (APIServer pid=1128487) WARNING 07-23 22:02:32 [vllm.py:1144] Inductor compilation was disabled by user settings, optimizations settings that are only active during inductor compilation will be ignored. |
| (APIServer pid=1128487) INFO 07-23 22:02:32 [kernel.py:292] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['vllm_c', 'native'], fused_add_rms_norm=['vllm_c', 'native']) |
| (APIServer pid=1128487) INFO 07-23 22:02:33 [vllm.py:1322] Cudagraph is disabled under eager mode |
| (APIServer pid=1128487) INFO 07-23 22:02:33 [compilation.py:312] Enabled custom fusions: norm_quant, act_quant |
| (EngineCore pid=1128629) INFO 07-23 22:02:45 [core.py:114] Initializing a V1 LLM engine (v0.25.0) with config: model='outputs/qwen35_pruned_keep25', speculative_config=None, tokenizer='outputs/qwen35_pruned_keep25', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=4096, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=2, 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=True, 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_mode='warn', jit_monitor_verbose=False), seed=0, served_model_name=student, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.NONE: 0>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['all'], 'ir_enable_torch_wrap': False, 'splitting_ops': [], '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, 'size_asserts': False, 'alignment_asserts': False, 'scalar_asserts': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.NONE: 0>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': True, 'fuse_act_quant': True, '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': 0, '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=['vllm_c', 'native'], fused_add_rms_norm=['vllm_c', 'native']), enable_flashinfer_autotune=True, enable_cutedsl_warmup=True, moe_backend='auto', linear_backend='auto') |
| (EngineCore pid=1128629) WARNING 07-23 22:02:45 [multiproc_executor.py:1067] Reducing Torch parallelism from 24 threads to 1 to avoid unnecessary CPU contention. Set OMP_NUM_THREADS in the external environment to tune this value as needed. |
| (EngineCore pid=1128629) INFO 07-23 22:02:45 [multiproc_executor.py:140] DP group leader: node_rank=0, node_rank_within_dp=0, master_addr=127.0.0.1, mq_connect_ip=192.168.0.15 (local), world_size=2, local_world_size=2 |
| (Worker pid=1128748) INFO 07-23 22:02:52 [parallel_state.py:1607] world_size=2 rank=0 local_rank=0 distributed_init_method=tcp://127.0.0.1:51069 backend=nccl |
| (Worker pid=1128749) INFO 07-23 22:02:52 [parallel_state.py:1607] world_size=2 rank=1 local_rank=1 distributed_init_method=tcp://127.0.0.1:51069 backend=nccl |
| (Worker pid=1128748) INFO 07-23 22:02:54 [pynccl.py:113] vLLM is using nccl==2.28.9 |
| (Worker pid=1128748) INFO 07-23 22:02:54 [cuda_communicator.py:264] Using ['PYNCCL'] all-reduce backends (in dispatch order) for group 'pp:0' out of potential backends: ['NCCL_SYMM_MEM', 'QUICK_REDUCE', 'FLASHINFER', 'AITER_CUSTOM', 'CUSTOM', 'SYMM_MEM', 'PYNCCL']. |
| (Worker pid=1128748) INFO 07-23 22:02:54 [parallel_state.py:1942] rank 0 in world size 2 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank 0, EPLB rank N/A |
| (Worker pid=1128748) INFO 07-23 22:02:54 [topk_topp_sampler.py:55] Using FlashInfer for top-p & top-k sampling. |
| (Worker_PP0 pid=1128748) INFO 07-23 22:02:55 [gpu_model_runner.py:5209] Starting to load model outputs/qwen35_pruned_keep25... |
| (Worker_PP0 pid=1128748) INFO 07-23 22:02:55 [qwen_gdn_linear_attn.py:228] Using Triton/FLA GDN prefill kernel (requested=auto, head_k_dim=128). |
| (Worker_PP0 pid=1128748) /home/henry/.cache/glean/megablocks-variable-93a1479bc15b/megablocks/grouped_gemm_util.py:10: UserWarning: Grouped GEMM not available. |
| (Worker_PP0 pid=1128748) warnings.warn('Grouped GEMM not available.') |
| (Worker_PP1 pid=1128749) /home/henry/.cache/glean/megablocks-variable-93a1479bc15b/megablocks/grouped_gemm_util.py:10: UserWarning: Grouped GEMM not available. |
| (Worker_PP1 pid=1128749) warnings.warn('Grouped GEMM not available.') |
| (Worker_PP0 pid=1128748) INFO 07-23 22:02:55 [cuda.py:476] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION']. |
| (Worker_PP0 pid=1128748) INFO 07-23 22:02:55 [flash_attn.py:718] Using FlashAttention version 2 |
| (Worker_PP0 pid=1128748) INFO 07-23 22:02:55 [weight_utils.py:849] Filesystem type for checkpoints: EXT4. Checkpoint size: 19.54 GiB. Available RAM: 106.98 GiB. |
| (Worker_PP0 pid=1128748) INFO 07-23 22:02:55 [weight_utils.py:872] 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. |
| (Worker_PP0 pid=1128748)
Loading safetensors checkpoint shards: 0% Completed | 0/1 [00:00<?, ?it/s] |
| (Worker_PP0 pid=1128748)
Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:05<00:00, 6.00s/it] |
| (Worker_PP0 pid=1128748)
Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:05<00:00, 6.00s/it] |
| (Worker_PP0 pid=1128748) |
| (Worker_PP0 pid=1128748) INFO 07-23 22:03:02 [default_loader.py:430] Loading weights took 6.46 seconds |
| (Worker_PP0 pid=1128748) INFO 07-23 22:03:02 [gpu_model_runner.py:5306] Model loading took 9.89 GiB memory and 6.722478 seconds |
| (Worker_PP0 pid=1128748) INFO 07-23 22:03:02 [interface.py:890] Setting attention block size to 544 tokens to ensure that attention page size is >= mamba page size. |
| (Worker_PP0 pid=1128748) INFO 07-23 22:03:02 [interface.py:914] Padding mamba page size by 1.49% to ensure that mamba page size and attention page size are exactly equal. |
| (Worker_PP1 pid=1128749) INFO 07-23 22:03:02 [interface.py:890] Setting attention block size to 544 tokens to ensure that attention page size is >= mamba page size. |
| (Worker_PP1 pid=1128749) INFO 07-23 22:03:02 [interface.py:914] Padding mamba page size by 1.49% to ensure that mamba page size and attention page size are exactly equal. |
| (Worker_PP0 pid=1128748) INFO 07-23 22:03:04 [gpu_worker.py:538] Available KV cache memory: 11.07 GiB |
| (EngineCore pid=1128629) INFO 07-23 22:03:04 [kv_cache_utils.py:2146] GPU KV cache size: 674,722 tokens |
| (EngineCore pid=1128629) INFO 07-23 22:03:04 [kv_cache_utils.py:2147] Maximum concurrency for 4,096 tokens per request: 164.73x |
| (Worker_PP0 pid=1128748) INFO 07-23 22:03:05 [cutedsl_warmup.py:97] Skipping CuTeDSL warmup because no compile units were requested. |
| (Worker_PP1 pid=1128749) INFO 07-23 22:03:05 [cutedsl_warmup.py:97] Skipping CuTeDSL warmup because no compile units were requested. |
| (Worker_PP0 pid=1128748) INFO 07-23 22:03:05 [jit_monitor.py:73] Kernel JIT monitor activated; monitored JIT compilations during inference will use mode=warn. |
| (Worker_PP1 pid=1128749) INFO 07-23 22:03:05 [jit_monitor.py:73] Kernel JIT monitor activated; monitored JIT compilations during inference will use mode=warn. |
| (EngineCore pid=1128629) INFO 07-23 22:03:05 [core.py:344] init engine (profile, create kv cache, warmup model) took 2.51 s |
| (EngineCore pid=1128629) INFO 07-23 22:03:07 [vllm.py:1042] Asynchronous scheduling is enabled. |
| (EngineCore pid=1128629) WARNING 07-23 22:03:07 [vllm.py:1096] Enforce eager set, disabling torch.compile and CUDAGraphs. This is equivalent to setting -cc.mode=none -cc.cudagraph_mode=none |
| (EngineCore pid=1128629) WARNING 07-23 22:03:07 [vllm.py:1144] Inductor compilation was disabled by user settings, optimizations settings that are only active during inductor compilation will be ignored. |
| (EngineCore pid=1128629) INFO 07-23 22:03:07 [kernel.py:292] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['vllm_c', 'native'], fused_add_rms_norm=['vllm_c', 'native']) |
| (EngineCore pid=1128629) INFO 07-23 22:03:07 [vllm.py:1322] Cudagraph is disabled under eager mode |
| (EngineCore pid=1128629) INFO 07-23 22:03:07 [compilation.py:312] Enabled custom fusions: norm_quant, act_quant |
| (APIServer pid=1128487) INFO 07-23 22:03:07 [api_server.py:612] Supported tasks: ['generate'] |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [hf.py:548] Detected the chat template content format to be 'openai'. You can set `--chat-template-content-format` to override this. |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [api_server.py:616] Starting vLLM server on http://127.0.0.1:8399 |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:37] Available routes are: |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /openapi.json, Methods: GET, HEAD |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /docs, Methods: GET, HEAD |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: GET, HEAD |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /redoc, Methods: GET, HEAD |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /load, Methods: GET |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /version, Methods: GET |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /health, Methods: GET |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /metrics, Methods: GET |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /tokenize, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /detokenize, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/models, Methods: GET |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /ping, Methods: GET |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /ping, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /invocations, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/chat/completions, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/chat/completions/batch, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/responses, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/responses/{response_id}, Methods: GET |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/responses/{response_id}/cancel, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/completions, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/messages, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/messages/count_tokens, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /generative_scoring, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /scale_elastic_ep, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /is_scaling_elastic_ep, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/chat/completions/render, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/completions/render, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/chat/completions/derender, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /v1/completions/derender, Methods: POST |
| (APIServer pid=1128487) INFO 07-23 22:03:09 [launcher.py:46] Route: /inference/v1/generate, Methods: POST |
| (APIServer pid=1128487) INFO: Started server process [1128487] |
| (APIServer pid=1128487) INFO: Waiting for application startup. |
| (APIServer pid=1128487) INFO: Application startup complete. |
| (APIServer pid=1128487) INFO: 127.0.0.1:33776 - "GET /health HTTP/1.1" 200 OK |
| (Worker_PP0 pid=1128748) WARNING 07-23 22:03:39 [jit_monitor.py:129] Triton kernel JIT compilation during inference: _zero_kv_blocks_kernel. This causes a latency spike; consider extending warmup to cover this shape/config. |
| (Worker_PP0 pid=1128748) WARNING 07-23 22:03:39 [jit_monitor.py:129] Triton kernel JIT compilation during inference: _compute_slot_mapping_kernel. This causes a latency spike; consider extending warmup to cover this shape/config. |
| (Worker_PP0 pid=1128748) WARNING 07-23 22:03:39 [jit_monitor.py:129] Triton kernel JIT compilation during inference: _causal_conv1d_fwd_kernel. This causes a latency spike; consider extending warmup to cover this shape/config. |
| (Worker_PP0 pid=1128748) WARNING 07-23 22:03:39 [jit_monitor.py:129] Triton kernel JIT compilation during inference: _fused_post_conv_kernel. This causes a latency spike; consider extending warmup to cover this shape/config. |
| (Worker_PP0 pid=1128748) WARNING 07-23 22:03:39 [jit_monitor.py:129] Triton kernel JIT compilation during inference: _build_route_rows. This causes a latency spike; consider extending warmup to cover this shape/config. |
| (Worker_PP0 pid=1128748) /home/henry/Documents/PythonProjects/variable-reap/vllm-plugin/.venv25/lib/python3.12/site-packages/vllm/distributed/parallel_state.py:813: UserWarning: The given buffer is not writable, and PyTorch does not support non-writable tensors. This means you can write to the underlying (supposedly non-writable) buffer using the tensor. You may want to copy the buffer to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_new.cpp:1586.) |
| (Worker_PP0 pid=1128748) object_tensor = torch.frombuffer(pickle.dumps(obj), dtype=torch.uint8) |
| [rank0]:[W723 22:03:39.319738400 ProcessGroupNCCL.cpp:4094] Warning: An unbatched P2P op (send/recv) was called on this ProcessGroup with size 2. In lazy initialization mode, this will result in a new 2-rank NCCL communicator to be created. (function operator()) |
| [rank1]:[W723 22:03:39.319996488 ProcessGroupNCCL.cpp:4094] Warning: An unbatched P2P op (send/recv) was called on this ProcessGroup with size 2. In lazy initialization mode, this will result in a new 2-rank NCCL communicator to be created. (function operator()) |
| (Worker_PP0 pid=1128748) WARNING 07-23 22:03:39 [jit_monitor.py:129] Triton kernel JIT compilation during inference: _causal_conv1d_update_kernel. This causes a latency spike; consider extending warmup to cover this shape/config. |
| (Worker_PP0 pid=1128748) WARNING 07-23 22:03:39 [jit_monitor.py:129] Triton kernel JIT compilation during inference: fused_recurrent_gated_delta_rule_packed_decode_kernel. This causes a latency spike; consider extending warmup to cover this shape/config. |
| (Worker_PP0 pid=1128748) WARNING 07-23 22:03:39 [jit_monitor.py:129] Triton kernel JIT compilation during inference: layer_norm_fwd_kernel. This causes a latency spike; consider extending warmup to cover this shape/config. |
| (APIServer pid=1128487) INFO 07-23 22:03:39 [loggers.py:273] Engine 000: Avg prompt throughput: 149.1 tokens/s, Avg generation throughput: 0.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0% |
| (Worker_PP0 pid=1128748) WARNING 07-23 22:03:39 [jit_monitor.py:129] Triton kernel JIT compilation during inference: fused_sigmoid_gating_delta_rule_update_kernel. This causes a latency spike; consider extending warmup to cover this shape/config. |
| (APIServer pid=1128487) INFO: 127.0.0.1:49612 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49654 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49692 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49738 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49658 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49648 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49618 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49786 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49680 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49636 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49788 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49670 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49802 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49840 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49774 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49872 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49886 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49692 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49844 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49878 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49654 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49612 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49658 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49626 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49858 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49738 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49680 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49768 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49818 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49786 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:03:49 [loggers.py:273] Engine 000: Avg prompt throughput: 6836.8 tokens/s, Avg generation throughput: 52.7 tokens/s, Running: 21 reqs, Waiting: 8 reqs, GPU KV cache usage: 7.0%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:49648 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49788 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49886 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49732 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49670 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49802 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49722 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49894 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49840 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49872 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49692 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49774 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49636 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49658 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49754 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49766 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49844 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49768 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49840 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49612 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49878 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49738 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49818 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49706 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49680 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49788 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49648 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49670 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49802 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49720 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49722 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49654 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:03:59 [loggers.py:273] Engine 000: Avg prompt throughput: 6998.9 tokens/s, Avg generation throughput: 79.4 tokens/s, Running: 29 reqs, Waiting: 0 reqs, GPU KV cache usage: 10.8%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:49618 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49648 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49802 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49878 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49670 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49626 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49722 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49618 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49654 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49894 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49692 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49754 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49636 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49802 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49786 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49658 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49720 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49732 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49844 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49774 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49872 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49738 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49818 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49768 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49802 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49858 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49636 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49766 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49818 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49788 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49844 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49732 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49774 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49886 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49670 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49722 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49738 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49768 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49766 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49818 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49878 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:04:09 [loggers.py:273] Engine 000: Avg prompt throughput: 5742.3 tokens/s, Avg generation throughput: 128.4 tokens/s, Running: 31 reqs, Waiting: 0 reqs, GPU KV cache usage: 10.4%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49858 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49612 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49706 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49754 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49618 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49626 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49654 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49840 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49648 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49802 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49872 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49738 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49894 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49844 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49878 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49788 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49886 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49636 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49670 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49768 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49818 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49680 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49732 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49722 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49766 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49774 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49786 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49720 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:04:19 [loggers.py:273] Engine 000: Avg prompt throughput: 461.0 tokens/s, Avg generation throughput: 82.5 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.7%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:49658 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:49692 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:33898 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:33902 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:33918 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:33932 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:33944 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:33960 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:33970 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:33996 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:34002 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:33980 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:04:29 [loggers.py:273] Engine 000: Avg prompt throughput: 860.2 tokens/s, Avg generation throughput: 18.6 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.2%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:34060 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:34044 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:34050 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:34028 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:04:39 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 86.1 tokens/s, Running: 6 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:34052 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:04:49 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 67.1 tokens/s, Running: 5 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:04:59 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 56.0 tokens/s, Running: 5 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:34006 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:05:09 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 46.9 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.9%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:05:19 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 44.8 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:05:29 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 45.2 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:05:39 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 44.4 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:05:49 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 44.4 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:05:59 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 44.8 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.2%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:06:09 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 44.8 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:06:19 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 44.8 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:34014 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:34032 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:34072 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:34076 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:46776 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:46736 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:46754 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:46742 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:46792 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:06:29 [loggers.py:273] Engine 000: Avg prompt throughput: 86.0 tokens/s, Avg generation throughput: 53.3 tokens/s, Running: 5 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:46714 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:46758 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:06:39 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 46.3 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.7%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:46700 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:06:49 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 28.5 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:06:59 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 22.4 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:07:09 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 22.4 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:07:19 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 22.4 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:46728 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:07:29 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 18.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:07:39 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:07:49 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:07:59 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:08:09 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:46766 - "POST /v1/chat/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:08:19 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 8.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:44578 - "GET /tokenizer_info HTTP/1.1" 404 Not Found |
| (APIServer pid=1128487) INFO: 127.0.0.1:44578 - "GET /tokenizer_info HTTP/1.1" 404 Not Found |
| (APIServer pid=1128487) INFO: 127.0.0.1:44578 - "GET /tokenizer_info HTTP/1.1" 404 Not Found |
| (APIServer pid=1128487) INFO 07-23 22:08:29 [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: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:08:39 [loggers.py:273] Engine 000: Avg prompt throughput: 107.1 tokens/s, Avg generation throughput: 57.2 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.2%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:08:49 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 111.0 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.2%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:08:59 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 112.0 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.2%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:09:09 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 111.0 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.2%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:09:19 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 112.0 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.8%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:09:29 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 110.0 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.8%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:09:39 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 111.0 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.8%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:09:49 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 112.0 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.8%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:09:59 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 111.0 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.8%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:38790 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:38802 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:38808 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:38822 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:38832 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:38838 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:38842 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:38852 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:38862 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:38872 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:10:09 [loggers.py:273] Engine 000: Avg prompt throughput: 692.5 tokens/s, Avg generation throughput: 100.9 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.8%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:58400 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:58386 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:58384 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:58420 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:58430 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:58444 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:58450 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:58464 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO: 127.0.0.1:58408 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:10:19 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 28.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO 07-23 22:10:29 [loggers.py:273] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0% |
| (APIServer pid=1128487) INFO: 127.0.0.1:58470 - "POST /v1/completions HTTP/1.1" 200 OK |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [launcher.py:100] [shutdown] API server: shutdown triggered |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [launcher.py:116] [shutdown] API server: stopping engine client mode=abort timeout=0s |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [core_client.py:655] [shutdown] MPClient: start timeout=0s |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [core_client.py:657] [shutdown] MPClient: stopping engine manager |
| (APIServer pid=1128487) WARNING 07-23 22:10:36 [utils.py:626] [shutdown] Process manager: force killing remaining processes count=1 |
| (EngineCore pid=1128629) INFO 07-23 22:10:36 [core.py:1214] [shutdown] EngineCore: trigger received signal=SIGTERM |
| (EngineCore pid=1128629) INFO 07-23 22:10:36 [core.py:1333] [shutdown] EngineCore: start mode=abort timeout=0s |
| (EngineCore pid=1128629) INFO 07-23 22:10:36 [core.py:1364] [shutdown] EngineCore: request processing complete; starting resource teardown |
| (EngineCore pid=1128629) INFO 07-23 22:10:36 [core.py:1227] [shutdown] EngineCore: exiting busy loop |
| (EngineCore pid=1128629) INFO 07-23 22:10:36 [multiproc_executor.py:426] [shutdown] Executor: waiting for worker exit count=2 |
| (Worker_PP0 pid=1128748) INFO 07-23 22:10:36 [multiproc_executor.py:790] Parent process exited, terminating worker queues |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [core_client.py:659] [shutdown] MPClient: engine manager stopped |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [core_client.py:660] [shutdown] MPClient: cleaning up background resources |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [core_client.py:662] [shutdown] MPClient: complete |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [launcher.py:125] [shutdown] API server: engine client stopped |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [launcher.py:128] [shutdown] API server: signalling HTTP server shutdown |
| (APIServer pid=1128487) INFO 07-23 22:10:36 [launcher.py:149] [shutdown] API server: shutting down FastAPI HTTP server |
| (APIServer pid=1128487) INFO: Shutting down |
| (APIServer pid=1128487) INFO: Waiting for application shutdown. |
| (APIServer pid=1128487) INFO: Application shutdown complete. |
| /home/henry/.local/share/uv/python/cpython-3.12.12-linux-x86_64-gnu/lib/python3.12/multiprocessing/resource_tracker.py:279: UserWarning: resource_tracker: There appear to be 2 leaked semaphore objects to clean up at shutdown |
| warnings.warn('resource_tracker: There appear to be %d ' |
| /home/henry/.local/share/uv/python/cpython-3.12.12-linux-x86_64-gnu/lib/python3.12/multiprocessing/resource_tracker.py:279: UserWarning: resource_tracker: There appear to be 3 leaked shared_memory objects to clean up at shutdown |
| warnings.warn('resource_tracker: There appear to be %d ' |
|
|
