PR #28975 Static Cache: load models with MQA or GQA

Static Cache: load models with MQA or GQA #28975

gante merged 4 commits into huggingface:main from gante:tiny_llama

load models with MHA or GQA

0b8888fa

load models with MHA or GQA

6e43bd02

gante changed the title ~~Static Cache: load models with MHA or GQA~~ Static Cache: load models with MQA or GQA 2 years ago

add test; make fixup

49fab562

gante marked this pull request as ready for review 2 years ago

gante requested a review from

ArthurZucker 2 years ago

better fn name

f0131f88

ArthurZucker approved these changes on 2024-02-13

gante merged 3e70a207 into main 2 years ago

gante deleted the tiny_llama branch 2 years ago

Reviewers

ArthurZucker

Assignees

No one assigned

Labels

None yet

Milestone

No milestone