llama.cpp
ggml : reuse quantum structs across backends
#5943
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
5
Changes
View On
GitHub
ggml : reuse quantum structs across backends
#5943
ggerganov
merged 5 commits into
master
from
gg/ggml-common-decl
ggerganov
added
demo
ggerganov
force pushed
from
07f35b33
2 years ago
ggerganov
force pushed
2 years ago
ggerganov
force pushed
to
7a8c0502
2 years ago
Base automatically changed from
gg/ggml-common
to
master
2 years ago
ggerganov
force pushed
2 years ago
ggerganov
force pushed
2 years ago
ggerganov
force pushed
2 years ago
ggerganov
removed
demo
ggerganov
added
need feedback
ggml : reuse quant blocks across backends
77414564
ggerganov
force pushed
to
77414564
2 years ago
ggerganov
marked this pull request as ready for review
2 years ago
Merge branch 'master' into gg/ggml-common-decl
54ebe70e
ikawrakow
commented on 2024-03-11
ggml : define helper constants only for CUDA and SYCL
dca5020a
ggerganov
force pushed
to
dca5020a
2 years ago
Merge branch 'master' into gg/ggml-common-decl
895f437e
ggml : define helper quantum constants for SYCL
66b88a80
ggerganov
merged
8030da7a
into master
2 years ago
ggerganov
deleted the gg/ggml-common-decl branch
2 years ago
Login to write a write a comment.
Login via GitHub
Reviewers
ikawrakow
Assignees
No one assigned
Labels
need feedback
Milestone
No milestone
Login to write a write a comment.
Login via GitHub