verl icon indicating copy to clipboard operation
verl copied to clipboard

vllm cannot load model after megatron training

Open KAKSIS opened this issue 7 months ago • 0 comments

After megatron training and convert to hf model, i want to infer using vllm, which meet problem when loading. File "/python3.11/site-packages/vllm/model_executor/models/utils.py", line 250, in _load_module raise ValueError(msg) ValueError: There is no module or parameter named 'decoder' in Qwen3ForCausalLM After model_merger.py process, the name of parameters changed.

KAKSIS avatar May 29 '25 10:05 KAKSIS