PR #10714 more perfo with llamafile tinyblas on x86_64.

more perfo with llamafile tinyblas on x86_64. #10714

slaren merged 5 commits into ggml-org:master from Djip007:perfo/tinyblas

github-actions added ggml

Djip007 marked this pull request as draft 1 year ago

Djip007 force pushed 1 year ago

Djip007 marked this pull request as ready for review 1 year ago

Djip007 force pushed 1 year ago

Djip007 marked this pull request as draft 1 year ago

Djip007 force pushed 1 year ago

slaren approved these changes on 2024-12-11

github-actions added examples

github-actions added python

github-actions added server

Djip007 commented on 2024-12-11

Djip007 force pushed 1 year ago

more perfo with llamafile tinyblas on x86_64.

3f2bc659

tinyblas dynamic dispaching

d7328741

sgemm: add M blocs.

ac2b53c5

Djip007 force pushed 1 year ago

github-actions added script

ggerganov approved these changes on 2024-12-23

- git 2.47 use short id of len 9.

22924d84

Djip007 force pushed 1 year ago

Djip007 marked this pull request as ready for review 1 year ago

Djip007 requested a review from

ngxson 1 year ago

ngxson commented on 2024-12-24

remove not stable test

2c6864a9

Djip007 force pushed to 2c6864a9 1 year ago

ngxson approved these changes on 2024-12-24

slaren merged 2cd43f49 into master 1 year ago

Reviewers

ngxson

ggerganov

slaren

Assignees

No one assigned

Labels

script examples python server ggml

Milestone

No milestone

llama.cpp more perfo with llamafile tinyblas on x86_64. #10714 Merged

more perfo with llamafile tinyblas on x86_64. #10714

llama.cpp
more perfo with llamafile tinyblas on x86_64.
#10714

Merged