python -m vllm.entrypoints.openai.api_server --model /models/llama-3.3-70b-instruct-fp8-dynamic --host localhost --port 10000 

INFO 01-14 13:24:33 api_server.py:712] vLLM API server version 0.6.6.post1 INFO 01-14 13:24:33 api_server.py:713] args: Namespace(host='localhost', port=10000, uvicorn_log_level='info', 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, 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='/data/textgen_cache/models/llama-3.3-70b-instruct-fp8-dynamic', task='auto', tokenizer=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, download_dir=None, load_format='auto', config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', quantization_param_path=None, max_model_len=None, guided_decoding_backend='xgrammar', logits_processor_pattern=None, distributed_executor_backend=None, worker_use_ray=False, pipeline_parallel_size=1, tensor_parallel_size=1, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=None, enable_prefix_caching=None, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=0, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=False, 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=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=None, qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', generation_config=None, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False) INFO 01-14 13:24:33 api_server.py:199] Started engine process with PID 11114 INFO 01-14 13:24:37 config.py:510] This model supports multiple tasks: {'embed', 'reward', 'generate', 'classify', 'score'}. Defaulting to 'generate'. WARNING 01-14 13:24:38 arg_utils.py:1103] Chunked prefill is enabled by default for models with max_model_len > 32K. Currently, chunked prefill might not work with some features or models. If you encounter any issues, please disable chunked prefill by setting --enable-chunked-prefill=False. INFO 01-14 13:24:38 config.py:1458] Chunked prefill is enabled with max_num_batched_tokens=2048. Traceback (most recent call last): File "<frozen runpy>", line 198, in _run_module_as_main File "<frozen runpy>", line 88, in _run_code File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 774, in <module> uvloop.run(run_server(args)) File "/home/ubuntu/venv/lib/python3.11/site-packages/uvloop/__init__.py", line 105, in run return runner.run(wrapper()) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3.11/asyncio/runners.py", line 120, in run return self._loop.run_until_complete(task) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete File "/home/ubuntu/venv/lib/python3.11/site-packages/uvloop/__init__.py", line 61, in wrapper return await main ^^^^^^^^^^ File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 740, in run_server async with build_async_engine_client(args) as engine_client: File "/usr/lib/python3.11/contextlib.py", line 204, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 118, in build_async_engine_client async with build_async_engine_client_from_engine_args( File "/usr/lib/python3.11/contextlib.py", line 204, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 210, in build_async_engine_client_from_engine_args engine_config = engine_args.create_engine_config() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/engine/arg_utils.py", line 1238, in create_engine_config config = VllmConfig( ^^^^^^^^^^^ File "<string>", line 18, in __init__ File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/config.py", line 3114, in __post_init__ self.quant_config = VllmConfig._get_quantization_config( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/config.py", line 3058, in _get_quantization_config quant_config = get_quant_config(model_config, load_config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/model_executor/model_loader/weight_utils.py", line 151, in get_quant_config return quant_cls.from_config(hf_quant_config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py", line 96, in from_config sparsity_scheme_map = cls._sparsity_scheme_map_from_config( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/venv/lib/python3.11/site-packages/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py", line 119, in _sparsity_scheme_map_from_config sparsity_config = SparsityCompressionConfig.model_validate( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/venv/lib/python3.11/site-packages/pydantic/main.py", line 627, in model_validate return cls.__pydantic_validator__.validate_python( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ pydantic_core._pydantic_core.ValidationError: 1 validation error for SparsityCompressionConfig format Field required [type=missing, input_value={}, input_type=dict] For further information visit https://errors.pydantic.dev/2.10/v/missing 

{ "_name_or_path": "/output/Llama-3.3-70B-Instruct-FP8-Dynamic", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [ 128001, 128008, 128009 ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "quantization_config": { "config_groups": { "group_0": { "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": null, "observer_kwargs": {}, "strategy": "token", "symmetric": true, "type": "float" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "strategy": "channel", "symmetric": true, "type": "float" } } }, "format": "float-quantized", "global_compression_ratio": 1.463543865167781, "ignore": [ "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {} }, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.47.0", "use_cache": true, "vocab_size": 128256 }