Skip to content

Commit fb0331f

Browse files
[Feature](ARD-2967) ard: add mqa score for spec decode for cape
Root Cause: add mqa score on gcu(currently only on xformers backend) vllm-project/vllm#9298 some according to vllm-project/vllm#9291 vllm-project/vllm#12093 Solution: add it Test: gcu Impact area: vllm Fix status: N/A Change-Id: I977305ba636741090478bb4721b97f297d4aac6c
1 parent ac87174 commit fb0331f

File tree

3 files changed

+1189
-0
lines changed

3 files changed

+1189
-0
lines changed

0 commit comments

Comments
 (0)