-
Notifications
You must be signed in to change notification settings - Fork 930
Issues: ggerganov/ggml
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. Weโll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Will the new K quantizations be added anytime soon for StarCoder?
#278
by richardr1126
was closed Sep 21, 2023
ggml : unified file format
documentation
Improvements or additions to documentation
enhancement
New feature or request
help wanted
Extra attention is needed
refactoring
Refactoring
#220
by philpax
was closed Nov 1, 2023
ggml : add mechanism to abort New feature or request
good first issue
Good for newcomers
ggml_graph_compute()
enhancement
#308
by ggerganov
was closed Jul 11, 2023
ggml : Good for newcomers
refactoring
Refactoring
ggml_graph_compute
should not require ggml_context
good first issue
#287
by ggerganov
was closed Jul 7, 2023
Is there interest in implementations of something analogous to
torch.Tensor.scatter_
and torch.gather
?
#718
by balisujohn
was closed Apr 20, 2024
ggml : new operations supported in New feature or request
encodec.cpp
enhancement
#281
by PABannier
was closed Jul 2, 2023
ggml : add NUMA support
enhancement
New feature or request
performance
Speed related topics
#290
by ggerganov
was closed Jun 26, 2023
ggml : make New feature or request
src0
broadcast-able into src1
for ggml_mul_mat()
enhancement
#289
by ggerganov
was closed Jul 12, 2023
ggml : add option for controlling work distribution across threads
performance
Speed related topics
refactoring
Refactoring
#291
by ggerganov
was closed Jan 5, 2024
GPT-J broken after transpose changes in ggml_new_tensor_2d
enhancement
New feature or request
#52
by djinn
was closed Apr 16, 2023
Previous Next
ProTip!
Add no:assignee to see everything thatโs not assigned.