Skip to content

GitLab

Unverified Commit ac3ed5a8 authored by Mandy Li's avatar Mandy Li Committed by GitHub
Browse files

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


Signed-off-by: default avatarmandy-li <mandy.j.li@intel.com>
parent e6ba2000
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/config/cache.py
View file @ ac3ed5a8
......@@ -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"]
......
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