FYI: Nvidia driver - 570, Cuda - 12.5 and Nvidia Container toolkit is installed too.
root:~# docker run -d --name vllmqwen --runtime=nvidia --gpus all -v ~/.cache/huggingface:/root/.cache/huggingface --env “HUGGING_FACE_HUB_TOKEN=” -p 8000:8000 --ipc=host vllm/vllm-openai:latest --model Qwen/Qwen2.5-14B-Instruct-AWQ --gpu-memory-utilization 0.95 --dtype float16 --enforce-eager --max-model-len 2048
2b6be09fe6f401fec0ebe2dde060a2caaac8edd0f6899c74a56a19e7a9229873
d
root:~# docker logs -f vllmqwen
INFO 05-07 23:00:43 [init.py:239] Automatically detected platform cuda.
INFO 05-07 23:00:48 [api_server.py:1043] vLLM API server version 0.8.5.post1
INFO 05-07 23:00:48 [api_server.py:1044] args: Namespace(host=None, port=8000, uvicorn_log_level=‘info’, disable_uvicorn_access_log=False, allow_credentials=False, allowed_origins=[‘‘], allowed_methods=[’’], allowed_headers=[‘‘], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format=‘auto’, response_role=‘assistant’, ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, enable_ssl_refresh=False, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, tool_call_parser=None, tool_parser_plugin=’‘, model=‘Qwen/Qwen2.5-14B-Instruct-AWQ’, task=‘auto’, tokenizer=None, hf_config_path=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode=‘auto’, trust_remote_code=False, allowed_local_media_path=None, load_format=‘auto’, download_dir=None, model_loader_extra_config={}, use_tqdm_on_load=True, config_format=<ConfigFormat.AUTO: ‘auto’>, dtype=‘float16’, max_model_len=2048, guided_decoding_backend=‘auto’, reasoning_parser=None, logits_processor_pattern=None, model_impl=‘auto’, distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=1, data_parallel_size=1, enable_expert_parallel=False, max_parallel_loading_workers=None, ray_workers_use_nsight=False, disable_custom_all_reduce=False, block_size=None, gpu_memory_utilization=0.95, swap_space=4, kv_cache_dtype=‘auto’, num_gpu_blocks_override=None, enable_prefix_caching=None, prefix_caching_hash_algo=‘builtin’, cpu_offload_gb=0, calculate_kv_scales=False, disable_sliding_window=False, use_v2_block_manager=True, seed=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_token=None, hf_overrides=None, enforce_eager=True, max_seq_len_to_capture=8192, tokenizer_pool_size=0, tokenizer_pool_type=‘ray’, tokenizer_pool_extra_config={}, limit_mm_per_prompt={}, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=None, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype=‘auto’, long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=None, max_prompt_adapters=1, max_prompt_adapter_token=0, device=‘auto’, speculative_config=None, ignore_patterns=[], served_model_name=None, qlora_adapter_name_or_path=None, show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, max_num_batched_tokens=None, max_num_seqs=None, max_num_partial_prefills=1, max_long_partial_prefills=1, long_prefill_token_threshold=0, num_lookahead_slots=0, scheduler_delay_factor=0.0, preemption_mode=None, num_scheduler_steps=1, multi_step_stream_outputs=True, scheduling_policy=‘fcfs’, enable_chunked_prefill=None, disable_chunked_mm_input=False, scheduler_cls=‘vllm.core.scheduler.Scheduler’, override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls=‘auto’, worker_extension_cls=’‘, generation_config=‘auto’, override_generation_config=None, enable_sleep_mode=False, additional_config=None, enable_reasoning=False, disable_cascade_attn=False, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, enable_server_load_tracking=False)
INFO 05-07 23:00:59 [config.py:717] This model supports multiple tasks: {‘generate’, ‘classify’, ‘score’, ‘embed’, ‘reward’}. Defaulting to ‘generate’.
WARNING 05-07 23:01:00 [config.py:830] awq quantization is not fully optimized yet. The speed can be slower than non-quantized models.
WARNING 05-07 23:01:00 [arg_utils.py:1658] Compute Capability < 8.0 is not supported by the V1 Engine. Falling back to V0.
WARNING 05-07 23:01:00 [cuda.py:93] To see benefits of async output processing, enable CUDA graph. Since, enforce-eager is enabled, async output processor cannot be used
INFO 05-07 23:01:00 [api_server.py:246] Started engine process with PID 48
INFO 05-07 23:01:05 [init.py:239] Automatically detected platform cuda.
INFO 05-07 23:01:07 [llm_engine.py:240] Initializing a V0 LLM engine (v0.8.5.post1) with config: model=‘Qwen/Qwen2.5-14B-Instruct-AWQ’, speculative_config=None, tokenizer=‘Qwen/Qwen2.5-14B-Instruct-AWQ’, skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.float16, max_seq_len=2048, download_dir=None, load_format=LoadFormat.AUTO, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=awq, enforce_eager=True, kv_cache_dtype=auto, device_config=cuda, decoding_config=DecodingConfig(guided_decoding_backend=‘auto’, reasoning_backend=None), observability_config=ObservabilityConfig(show_hidden_metrics=False, otlp_traces_endpoint=None, collect_model_forward_time=False, collect_model_execute_time=False), seed=None, served_model_name=Qwen/Qwen2.5-14B-Instruct-AWQ, num_scheduler_steps=1, multi_step_stream_outputs=True, enable_prefix_caching=None, chunked_prefill_enabled=False, use_async_output_proc=False, disable_mm_preprocessor_cache=False, mm_processor_kwargs=None, pooler_config=None, compilation_config={“splitting_ops”:[],“compile_sizes”:[],“cudagraph_capture_sizes”:[],“max_capture_size”:0}, use_cached_outputs=True,
INFO 05-07 23:01:09 [cuda.py:240] Cannot use FlashAttention-2 backend for Volta and Turing GPUs.
INFO 05-07 23:01:09 [cuda.py:289] Using XFormers backend.
INFO 05-07 23:01:11 [parallel_state.py:1004] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, TP rank 0
INFO 05-07 23:01:11 [model_runner.py:1108] Starting to load model Qwen/Qwen2.5-14B-Instruct-AWQ…
INFO 05-07 23:01:12 [weight_utils.py:265] Using model weights format [’.safetensors’]
Loading safetensors checkpoint shards: 0% Completed | 0/3 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 33% Completed | 1/3 [00:00<00:01, 1.40it/s]
Loading safetensors checkpoint shards: 67% Completed | 2/3 [00:02<00:01, 1.21s/it]
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:03<00:00, 1.38s/it]
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:03<00:00, 1.28s/it]
INFO 05-07 23:01:16 [loader.py:458] Loading weights took 3.97 seconds
INFO 05-07 23:01:16 [model_runner.py:1140] Model loading took 9.3722 GiB and 5.167720 seconds
INFO 05-07 23:01:19 [worker.py:287] Memory profiling takes 2.95 seconds
INFO 05-07 23:01:19 [worker.py:287] the current vLLM instance can use total_gpu_memory (14.56GiB) x gpu_memory_utilization (0.95) = 13.84GiB
INFO 05-07 23:01:19 [worker.py:287] model weights take 9.37GiB; non_torch_memory takes 0.05GiB; PyTorch activation peak memory takes 1.41GiB; the rest of the memory reserved for KV Cache is 3.01GiB.
INFO 05-07 23:01:20 [executor_base.py:112] # cuda blocks: 1027, # CPU blocks: 1365
INFO 05-07 23:01:20 [executor_base.py:117] Maximum concurrency for 2048 tokens per request: 8.02x
ERROR 05-07 23:01:21 [engine.py:448] CUDA error: invalid argument
ERROR 05-07 23:01:21 [engine.py:448] CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
ERROR 05-07 23:01:21 [engine.py:448] For debugging consider passing CUDA_LAUNCH_BLOCKING=1
ERROR 05-07 23:01:21 [engine.py:448] Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
ERROR 05-07 23:01:21 [engine.py:448] Traceback (most recent call last):
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py”, line 436, in run_mp_engine
ERROR 05-07 23:01:21 [engine.py:448] engine = MQLLMEngine.from_vllm_config(
ERROR 05-07 23:01:21 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py”, line 128, in from_vllm_config
ERROR 05-07 23:01:21 [engine.py:448] return cls(
Process SpawnProcess-1:
ERROR 05-07 23:01:21 [engine.py:448] ^^^^
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py”, line 82, in init
ERROR 05-07 23:01:21 [engine.py:448] self.engine = LLMEngine(*args, **kwargs)
ERROR 05-07 23:01:21 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/engine/llm_engine.py”, line 278, in init
ERROR 05-07 23:01:21 [engine.py:448] self._initialize_kv_caches()
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/engine/llm_engine.py”, line 435, in _initialize_kv_caches
ERROR 05-07 23:01:21 [engine.py:448] self.model_executor.initialize_cache(num_gpu_blocks, num_cpu_blocks)
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/executor/executor_base.py”, line 123, in initialize_cache
ERROR 05-07 23:01:21 [engine.py:448] self.collective_rpc(“initialize_cache”,
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/executor/uniproc_executor.py”, line 56, in collective_rpc
ERROR 05-07 23:01:21 [engine.py:448] answer = run_method(self.driver_worker, method, args, kwargs)
ERROR 05-07 23:01:21 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/utils.py”, line 2456, in run_method
ERROR 05-07 23:01:21 [engine.py:448] return func(*args, **kwargs)
ERROR 05-07 23:01:21 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/worker/worker.py”, line 327, in initialize_cache
ERROR 05-07 23:01:21 [engine.py:448] self._init_cache_engine()
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/worker/worker.py”, line 333, in _init_cache_engine
ERROR 05-07 23:01:21 [engine.py:448] CacheEngine(self.cache_config, self.model_config,
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/worker/cache_engine.py”, line 66, in init
ERROR 05-07 23:01:21 [engine.py:448] self.cpu_cache = self._allocate_kv_cache(self.num_cpu_blocks, “cpu”)
ERROR 05-07 23:01:21 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 05-07 23:01:21 [engine.py:448] File “/usr/local/lib/python3.12/dist-packages/vllm/worker/cache_engine.py”, line 95, in _allocate_kv_cache
ERROR 05-07 23:01:21 [engine.py:448] layer_kv_cache = torch.zeros(
ERROR 05-07 23:01:21 [engine.py:448] ^^^^^^^^^^^^
ERROR 05-07 23:01:21 [engine.py:448] RuntimeError: CUDA error: invalid argument
ERROR 05-07 23:01:21 [engine.py:448] CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
ERROR 05-07 23:01:21 [engine.py:448] For debugging consider passing CUDA_LAUNCH_BLOCKING=1
ERROR 05-07 23:01:21 [engine.py:448] Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
ERROR 05-07 23:01:21 [engine.py:448]
Traceback (most recent call last):
File “/usr/lib/python3.12/multiprocessing/process.py”, line 314, in _bootstrap
self.run()
File “/usr/lib/python3.12/multiprocessing/process.py”, line 108, in run
self._target(*self._args, **self._kwargs)
File “/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py”, line 450, in run_mp_engine
raise e
File “/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py”, line 436, in run_mp_engine
engine = MQLLMEngine.from_vllm_config(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py”, line 128, in from_vllm_config
return cls(
^^^^
File “/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py”, line 82, in init
self.engine = LLMEngine(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/usr/local/lib/python3.12/dist-packages/vllm/engine/llm_engine.py”, line 278, in init
self._initialize_kv_caches()
File “/usr/local/lib/python3.12/dist-packages/vllm/engine/llm_engine.py”, line 435, in _initialize_kv_caches
self.model_executor.initialize_cache(num_gpu_blocks, num_cpu_blocks)
File “/usr/local/lib/python3.12/dist-packages/vllm/executor/executor_base.py”, line 123, in initialize_cache
self.collective_rpc(“initialize_cache”,
File “/usr/local/lib/python3.12/dist-packages/vllm/executor/uniproc_executor.py”, line 56, in collective_rpc
answer = run_method(self.driver_worker, method, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/usr/local/lib/python3.12/dist-packages/vllm/utils.py”, line 2456, in run_method
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File “/usr/local/lib/python3.12/dist-packages/vllm/worker/worker.py”, line 327, in initialize_cache
self._init_cache_engine()
File “/usr/local/lib/python3.12/dist-packages/vllm/worker/worker.py”, line 333, in _init_cache_engine
CacheEngine(self.cache_config, self.model_config,
File “/usr/local/lib/python3.12/dist-packages/vllm/worker/cache_engine.py”, line 66, in init
self.cpu_cache = self._allocate_kv_cache(self.num_cpu_blocks, “cpu”)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/usr/local/lib/python3.12/dist-packages/vllm/worker/cache_engine.py”, line 95, in _allocate_kv_cache
layer_kv_cache = torch.zeros(
^^^^^^^^^^^^
RuntimeError: CUDA error: invalid argument
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
[rank0]:[W507 23:01:21.158637882 ProcessGroupNCCL.cpp:1496] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see Distributed communication package - torch.distributed — PyTorch 2.7 documentation (function operator())
Traceback (most recent call last):
File “”, line 198, in _run_module_as_main
File “”, line 88, in _run_code
File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py”, line 1130, in
uvloop.run(run_server(args))
File “/usr/local/lib/python3.12/dist-packages/uvloop/init.py”, line 109, in run
return __asyncio.run(
^^^^^^^^^^^^^^
File “/usr/lib/python3.12/asyncio/runners.py”, line 195, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File “/usr/lib/python3.12/asyncio/runners.py”, line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “uvloop/loop.pyx”, line 1518, in uvloop.loop.Loop.run_until_complete
File “/usr/local/lib/python3.12/dist-packages/uvloop/init.py”, line 61, in wrapper
return await main
^^^^^^^^^^
File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py”, line 1078, in run_server
async with build_async_engine_client(args) as engine_client:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/usr/lib/python3.12/contextlib.py”, line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py”, line 146, in build_async_engine_client
async with build_async_engine_client_from_engine_args(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/usr/lib/python3.12/contextlib.py”, line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py”, line 269, in build_async_engine_client_from_engine_args
raise RuntimeError(
RuntimeError: Engine process failed to start. See stack trace for the root cause.