Commit 058b32ae authored by zhuwenwen's avatar zhuwenwen
Browse files

set VLLM_USE_NN=1

parent d48d7497
...@@ -969,7 +969,7 @@ environment_variables: dict[str, Callable[[], Any]] = { ...@@ -969,7 +969,7 @@ environment_variables: dict[str, Callable[[], Any]] = {
# If set, vLLM will transpose weight to use nn layout # If set, vLLM will transpose weight to use nn layout
"VLLM_USE_NN": "VLLM_USE_NN":
lambda: (os.environ.get("VLLM_USE_NN", "False").lower() in lambda: (os.environ.get("VLLM_USE_NN", "True").lower() in
("true", "1")), ("true", "1")),
# Enable two batch overlap. # Enable two batch overlap.
......
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