OPEA

/

Mistral-Small-3.1-24B-Instruct-2503-int4-AutoRound-awq-sym

like 16

Follow

Open Platform for Enterprise AI 76

I'm trying to use this model for tooling but vllm throws a fit:

vllm-server-mistral-31  | 2025-05-13T18:34:19.348751933Z INFO 05-13 11:34:19 [api_server.py:1044] args: Namespace(host='0.0.0.0', port=8901, 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=True, tool_call_parser='mistral', tool_parser_plugin='', model='OPEA/Mistral-Small-3.1-24B-Instruct-2503-int4-AutoRound-awq-sym', task='auto', tokenizer=None, hf_config_path=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='mistral', trust_remote_code=False, allowed_local_media_path=None, load_format='mistral', download_dir=None, model_loader_extra_config={}, use_tqdm_on_load=True, config_format='mistral', dtype='auto', max_model_len=8192, guided_decoding_backend='xgrammar', reasoning_parser=None, logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=2, 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=0.9, swap_space=16.0, 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=False, 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=1, 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=KVTransferConfig(kv_connector='LMCacheConnector', kv_buffer_device='cuda', kv_buffer_size=1000000000.0, kv_role='kv_both', kv_rank=None, kv_parallel_size=1, kv_ip='127.0.0.1', kv_port=14579, kv_connector_extra_config={}), worker_cls='auto', worker_extension_cls='', generation_config='auto', override_generation_config={'temperature': 0.15}, 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)
vllm-server-mistral-31  | 2025-05-13T18:34:19.427952091Z Traceback (most recent call last):
vllm-server-mistral-31  | 2025-05-13T18:34:19.427984708Z   File "<frozen runpy>", line 198, in _run_module_as_main
vllm-server-mistral-31  | 2025-05-13T18:34:19.427993161Z   File "<frozen runpy>", line 88, in _run_code
vllm-server-mistral-31  | 2025-05-13T18:34:19.427998414Z   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 1130, in <module>
vllm-server-mistral-31  | 2025-05-13T18:34:19.428236806Z     uvloop.run(run_server(args))
vllm-server-mistral-31  | 2025-05-13T18:34:19.428301588Z   File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 109, in run
vllm-server-mistral-31  | 2025-05-13T18:34:19.428383563Z     return __asyncio.run(
vllm-server-mistral-31  | 2025-05-13T18:34:19.428400056Z            ^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.428404091Z   File "/usr/lib/python3.12/asyncio/runners.py", line 195, in run
vllm-server-mistral-31  | 2025-05-13T18:34:19.428525418Z     return runner.run(main)
vllm-server-mistral-31  | 2025-05-13T18:34:19.428555912Z            ^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.428564216Z   File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
vllm-server-mistral-31  | 2025-05-13T18:34:19.428651938Z     return self._loop.run_until_complete(task)
vllm-server-mistral-31  | 2025-05-13T18:34:19.428673567Z            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.428681990Z   File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
vllm-server-mistral-31  | 2025-05-13T18:34:19.428850653Z   File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 61, in wrapper
vllm-server-mistral-31  | 2025-05-13T18:34:19.428912460Z     return await main
vllm-server-mistral-31  | 2025-05-13T18:34:19.428935147Z            ^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.428946993Z   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 1078, in run_server
vllm-server-mistral-31  | 2025-05-13T18:34:19.429147008Z     async with build_async_engine_client(args) as engine_client:
vllm-server-mistral-31  | 2025-05-13T18:34:19.429180720Z                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.429188442Z   File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
vllm-server-mistral-31  | 2025-05-13T18:34:19.429271101Z     return await anext(self.gen)
vllm-server-mistral-31  | 2025-05-13T18:34:19.429299002Z            ^^^^^^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.429308019Z   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 146, in build_async_engine_client
vllm-server-mistral-31  | 2025-05-13T18:34:19.429378026Z     async with build_async_engine_client_from_engine_args(
vllm-server-mistral-31  | 2025-05-13T18:34:19.429396912Z                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.429400493Z   File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
vllm-server-mistral-31  | 2025-05-13T18:34:19.429476041Z     return await anext(self.gen)
vllm-server-mistral-31  | 2025-05-13T18:34:19.429508481Z            ^^^^^^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.429519000Z   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 166, in build_async_engine_client_from_engine_args
vllm-server-mistral-31  | 2025-05-13T18:34:19.429588733Z     vllm_config = engine_args.create_engine_config(usage_context=usage_context)
vllm-server-mistral-31  | 2025-05-13T18:34:19.429630437Z                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.429640062Z   File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 1099, in create_engine_config
vllm-server-mistral-31  | 2025-05-13T18:34:19.429885961Z     model_config = self.create_model_config()
vllm-server-mistral-31  | 2025-05-13T18:34:19.429923383Z                    ^^^^^^^^^^^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.429932504Z   File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 987, in create_model_config
vllm-server-mistral-31  | 2025-05-13T18:34:19.430129521Z     return ModelConfig(
vllm-server-mistral-31  | 2025-05-13T18:34:19.430139732Z            ^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.430157084Z   File "/usr/local/lib/python3.12/dist-packages/vllm/config.py", line 451, in __init__
vllm-server-mistral-31  | 2025-05-13T18:34:19.430269986Z     hf_config = get_config(self.hf_config_path or self.model,
vllm-server-mistral-31  | 2025-05-13T18:34:19.430292845Z                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.430298657Z   File "/usr/local/lib/python3.12/dist-packages/vllm/transformers_utils/config.py", line 347, in get_config
vllm-server-mistral-31  | 2025-05-13T18:34:19.430406913Z     config = load_params_config(model, revision, token=HF_TOKEN, **kwargs)
vllm-server-mistral-31  | 2025-05-13T18:34:19.430450512Z              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
vllm-server-mistral-31  | 2025-05-13T18:34:19.430460838Z   File "/usr/local/lib/python3.12/dist-packages/vllm/transformers_utils/config.py", line 654, in load_params_config
vllm-server-mistral-31  | 2025-05-13T18:34:19.430591408Z     raise ValueError(
vllm-server-mistral-31  | 2025-05-13T18:34:19.430604416Z ValueError: Failed to load mistral 'params.json' config for model OPEA/Mistral-Small-3.1-24B-Instruct-2503-int4-AutoRound-awq-sym. Please check if the model is a mistral-format model and if the config file exists.