fix: consider kv cache 64 align to estimate kv cache memory size #417
+9
−1
Annotations
1 error
|
Run amannn/action-semantic-pull-request@v5
No release type found in pull request title "fix : consider kv cache 64 align to estimate kv cache memory size". Add a prefix to indicate what kind of release this pull request corresponds to. For reference, see https://www.conventionalcommits.org/
Available types:
- release
- feature
- model
- core
- fix
- perf
- refactor
- docs
- other
|
Loading