Skip to content

GitLab

Unverified Commit b5dd5e87 authored by Peng Zhang's avatar Peng Zhang Committed by GitHub
Browse files

chore: remove unnecessary limits on quantization methods in test script (#7997)

parent 9379da77
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 4 deletions
test/srt/test_vllm_dependency.py
View file @ b5dd5e87
......@@ -42,10 +42,6 @@ def popen_launch_server_wrapper(base_url, model, is_fp8, is_tp2):
other_args.extend(["--tp", "2"])
if "DeepSeek" in model:
other_args.extend(["--mem-frac", "0.85"])
if "AWQ" in model:
other_args.extend(["--quantization", "awq"])
elif "GPTQ" in model:
other_args.extend(["--quantization", "gptq"])
process = popen_launch_server(
model,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment