owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

correct access to "args" dictionary

Browse Source
This commit is contained in:
mohamednaji7
2025-01-21 22:33:28 +02:00
parent 8882f6d50b
commit 131c17569f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/engine_args.py
+2 -2
View File
@@ -147,8 +147,8 @@ def get_engine_args():
# Rename and match to vllm args # Rename and match to vllm args
args = match_vllm_args(args) args = match_vllm_args(args)
if args.load_format=="bitsandbytes": if args.get("load_format") == "bitsandbytes":
args.quantization = args.load_format args["quantization"] = args["load_format"]
# Set tensor parallel size and max parallel loading workers if more than 1 GPU is available # Set tensor parallel size and max parallel loading workers if more than 1 GPU is available
num_gpus = device_count() num_gpus = device_count()