Skip to content

GitLab

Commit 2907adfa authored by zhuwenwen's avatar zhuwenwen
Browse files

暂不支持awq的scale和zero合并操作

parent d3fa2342
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
vllm/model_executor/model_loader/utils.py
View file @ 2907adfa
...@@ -252,8 +252,8 @@ def _get_model_architecture(model_config: ModelConfig) -> tuple[type[nn.Module], ...@@ -252,8 +252,8 @@ def _get_model_architecture(model_config: ModelConfig) -> tuple[type[nn.Module],
# awq相关配置 # awq相关配置
try: try:
if os.getenv('AWQ_MOE_SZ') == None: # if os.getenv('AWQ_MOE_SZ') == None:
os.environ['AWQ_MOE_SZ'] = '1' # os.environ['AWQ_MOE_SZ'] = '1'
if os.getenv('AWQ_PAD') == None and (torch.cuda.get_device_properties(torch.cuda.current_device()).multi_processor_count == 120): if os.getenv('AWQ_PAD') == None and (torch.cuda.get_device_properties(torch.cuda.current_device()).multi_processor_count == 120):
os.environ['AWQ_PAD'] = '1' os.environ['AWQ_PAD'] = '1'
except Exception as e: except Exception as e:
......
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