Skip to content

GitLab

Commit 22839191 authored by zhuwenwen's avatar zhuwenwen
Browse files

set default layout

parent bb73b5a6
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
vllm/model_executor/model_loader/utils.py
View file @ 22839191
...@@ -29,6 +29,8 @@ def get_model_architecture( ...@@ -29,6 +29,8 @@ def get_model_architecture(
os.environ['GEMM_PAD'] = '1' os.environ['GEMM_PAD'] = '1'
if os.getenv('FA_PAD') != '1': if os.getenv('FA_PAD') != '1':
os.environ['FA_PAD'] = '0' os.environ['FA_PAD'] = '0'
else:
os.environ['LLAMA_NN'] = '0'
# Special handling for quantized Mixtral. # Special handling for quantized Mixtral.
# FIXME(woosuk): This is a temporary hack. # FIXME(woosuk): This is a temporary hack.
if (model_config.quantization is not None if (model_config.quantization is not None
......
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