1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
|
=== Local LLM Reward Model Batch Test ===
Model: models/llama-3.1-8b-instruct
GPU: NVIDIA A100-SXM4-40GB
Starting vLLM server on port 8005...
Waiting for vLLM server to start...
[0;36m(APIServer pid=2801991)[0;0m INFO 01-27 11:59:38 [api_server.py:1351] vLLM API server version 0.13.0
[0;36m(APIServer pid=2801991)[0;0m INFO 01-27 11:59:38 [utils.py:253] non-default args: {'port': 8005, 'model': 'models/llama-3.1-8b-instruct', 'dtype': 'bfloat16', 'max_model_len': 4096, 'gpu_memory_utilization': 0.85}
[0;36m(APIServer pid=2801991)[0;0m INFO 01-27 11:59:39 [model.py:514] Resolved architecture: LlamaForCausalLM
[0;36m(APIServer pid=2801991)[0;0m INFO 01-27 11:59:39 [model.py:1661] Using max model len 4096
[0;36m(APIServer pid=2801991)[0;0m INFO 01-27 11:59:40 [scheduler.py:230] Chunked prefill is enabled with max_num_batched_tokens=2048.
[0;36m(EngineCore_DP0 pid=2802146)[0;0m INFO 01-27 11:59:52 [core.py:93] Initializing a V1 LLM engine (v0.13.0) with config: model='models/llama-3.1-8b-instruct', speculative_config=None, tokenizer='models/llama-3.1-8b-instruct', 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=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, 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), seed=0, served_model_name=models/llama-3.1-8b-instruct, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::kda_attention', 'vllm::sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_split_points': [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, 'eliminate_noops': True, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False}, 'max_cudagraph_capture_size': 512, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False}, 'local_cache_dir': None}
[0;36m(EngineCore_DP0 pid=2802146)[0;0m INFO 01-27 11:59:54 [parallel_state.py:1203] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://141.142.254.34:42557 backend=nccl
[0;36m(EngineCore_DP0 pid=2802146)[0;0m INFO 01-27 11:59:54 [parallel_state.py:1411] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank 0
[0;36m(EngineCore_DP0 pid=2802146)[0;0m INFO 01-27 11:59:56 [gpu_model_runner.py:3562] Starting to load model models/llama-3.1-8b-instruct...
[0;36m(EngineCore_DP0 pid=2802146)[0;0m INFO 01-27 11:59:57 [cuda.py:351] Using FLASH_ATTN attention backend out of potential backends: ('FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION')
ERROR: vLLM server failed to start
|
