frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-02-28 23:09:14 -08:00
committed by GitHub
parent fdcc405346
commit 3b5567a209
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/platforms/cuda.py
View File

@ -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: