neuralmagic

/

Mistral-Nemo-Instruct-2407-FP8

like 13

export MODEL_DIR=/root/workspace/model/neuralmagic/Mistral-Nemo-Instruct-2407-FP8
export MODEL_NAME=neuralmagic/Mistral-Nemo-Instruct-2407-FP8
export MAX_MODEL_LEN=16384
CUDA_VISIBLE_DEVICES=0 python3 -m vllm.entrypoints.openai.api_server --tensor-parallel-size 1 --quantization="fp8" --host 0.0.0.0 --port 8080 --disable-log-requests --model $MODEL_DIR --served-model-name $MODEL_NAME --max-model-len $MAX_MODEL_LEN

WARNING 07-19 03:04:14 fp8.py:48] Detected fp8 checkpoint. Please note that the format is experimental and subject to change.
[rank0]: Traceback (most recent call last):
[rank0]:   File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
[rank0]:     return _run_code(code, main_globals, None,
[rank0]:   File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
[rank0]:     exec(code, run_globals)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/api_server.py", line 196, in <module>
[rank0]:     engine = AsyncLLMEngine.from_engine_args(
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 395, in from_engine_args
[rank0]:     engine = cls(
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 349, in __init__
[rank0]:     self.engine = self._init_engine(*args, **kwargs)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 470, in _init_engine
[rank0]:     return engine_class(*args, **kwargs)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/engine/llm_engine.py", line 223, in __init__
[rank0]:     self.model_executor = executor_class(
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/executor/executor_base.py", line 41, in __init__
[rank0]:     self._init_executor()
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/executor/gpu_executor.py", line 24, in _init_executor
[rank0]:     self.driver_worker.load_model()
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 121, in load_model
[rank0]:     self.model_runner.load_model()
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 147, in load_model
[rank0]:     self.model = get_model(
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/model_loader/__init__.py", line 21, in get_model
[rank0]:     return loader.load_model(model_config=model_config,
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/model_loader/loader.py", line 249, in load_model
[rank0]:     model.load_weights(
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 416, in load_weights
[rank0]:     weight_loader(param, loaded_weight, shard_id)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/layers/linear.py", line 662, in weight_loader
[rank0]:     loaded_weight = loaded_weight.narrow(output_dim, start_idx,
[rank0]: RuntimeError: start (0) + length (1280) exceeds dimension size (1024).