Skip to content

GitLab

Unverified Commit 18563f20 authored by Chauncey's avatar Chauncey Committed by GitHub
Browse files

[Misc] Reduce attention logging levels (#40086) 


Signed-off-by: default avatarchaunceyjiang <chaunceyjiang@gmail.com>
parent 0e884fe6
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/layers/attention/attention.py
View file @ 18563f20
...@@ -259,7 +259,7 @@ class Attention(nn.Module, AttentionLayerBase): ...@@ -259,7 +259,7 @@ class Attention(nn.Module, AttentionLayerBase):
if skip: if skip:
kv_cache_dtype = "auto" kv_cache_dtype = "auto"
calculate_kv_scales = False calculate_kv_scales = False
logger.info( logger.debug(
"Layer %s: kv_cache_dtype=%s, sliding_window=%s", "Layer %s: kv_cache_dtype=%s, sliding_window=%s",
prefix, prefix,
kv_cache_dtype, kv_cache_dtype,
......
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