Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "504ac53d18fc057d2a98741fa27d89df9054422d"
Unverified Commit 3b5567a2 authored by Woosuk Kwon's avatar Woosuk Kwon Committed by GitHub
Browse files

[V1][Minor] Do not print attn backend twice (#13985) 


Signed-off-by: default avatarWoosuk Kwon <woosuk.kwon@berkeley.edu>
parent fdcc4053
Hide whitespace changes
Inline Side-by-side
Showing with 4 additions and 3 deletions
vllm/platforms/cuda.py
View file @ 3b5567a2
......@@ -178,7 +178,8 @@ class CudaPlatformBase(Platform):
block_size)
else:
if use_v1:
logger.info("Using FlashMLA backend on V1 engine.")
logger.info_once(
"Using FlashMLA backend on V1 engine.")
return ("vllm.v1.attention.backends.mla."
"flashmla.FlashMLABackend")
else:
......@@ -187,14 +188,14 @@ class CudaPlatformBase(Platform):
"flashmla.FlashMLABackend")
if use_v1:
logger.info("Using Triton MLA backend on V1 engine.")
logger.info_once("Using Triton MLA backend on V1 engine.")
return ("vllm.v1.attention.backends.mla."
"triton_mla.TritonMLABackend")
else:
logger.info("Using Triton MLA backend.")
return "vllm.attention.backends.triton_mla.TritonMLABackend"
if use_v1:
logger.info("Using Flash Attention backend on V1 engine.")
logger.info_once("Using Flash Attention backend on V1 engine.")
return ("vllm.v1.attention.backends.flash_attn."
"FlashAttentionBackend")
if selected_backend == _Backend.FLASHINFER:
......
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