xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-23 21:54:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

Support block size of 256 used by Intel HPU (#26883)

Browse Source 
Signed-off-by: mandy-li <mandy.j.li@intel.com>
This commit is contained in:
Mandy Li 2025-10-16 12:10:57 -07:00 committed by GitHub
parent e6ba2000ae
commit ac3ed5a815
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config/cache.py
View File

@ -19,7 +19,7 @@ else:
logger = init_logger(__name__)
BlockSize = Literal[1, 8, 16, 32, 64, 128]
BlockSize = Literal[1, 8, 16, 32, 64, 128, 256]
CacheDType = Literal["auto", "bfloat16", "fp8", "fp8_e4m3", "fp8_e5m2", "fp8_inc"]
MambaDType = Literal["auto", "float32"]
PrefixCachingHashAlgo = Literal["sha256", "sha256_cbor"]