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

add test cases

Browse Source 
Former-commit-id: b27269bd2b
This commit is contained in:
hiyouga
2024-06-15 04:05:54 +08:00
parent d4ce280fbc
commit a3f4925c2c
9 changed files with 184 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/chat/vllm_engine.py
View File

@@ -52,7 +52,7 @@ class VllmEngine(BaseEngine):
"model": model_args.model_name_or_path,
"trust_remote_code": True,
"download_dir": model_args.cache_dir,
"dtype": model_args.vllm_dtype,
"dtype": model_args.infer_dtype,
"max_model_len": model_args.vllm_maxlen,
"tensor_parallel_size": get_device_count() or 1,
"gpu_memory_utilization": model_args.vllm_gpu_util,