423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-15 03:10:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: pass the max_lora_rank parameter to vLLM backend

Browse Source 
Former-commit-id: b20d62ba3c
This commit is contained in:
juejuezi
2024-05-17 16:07:39 +08:00
parent 9af3dce3c8
commit 20326affde
2 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llamafactory/chat/vllm_engine.py
View File

@@ -59,6 +59,7 @@ class VllmEngine(BaseEngine):
"disable_log_requests": True,
"enforce_eager": model_args.vllm_enforce_eager,
"enable_lora": model_args.adapter_name_or_path is not None,
"max_lora_rank": model_args.vllm_max_lora_rank,
}
if model_args.visual_inputs: