Skip to content

Issues: ggerganov/ggml

ggml : unified file format
#220 by philpax was closed Nov 1, 2023
Closed 82
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.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
212 Open 169 Closed
212 Open 169 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

ggml : make src0 broadcast-able into src1 for ggml_mul_mat() enhancement New feature or request
#289 by ggerganov was closed Jul 12, 2023 updated Jul 12, 2023
1
@ggerganov
1
Why is GGML so much faster than PyTorch?
#382 by wizardforcel was closed Jul 14, 2023 updated Jul 14, 2023
2
[suggestion] unit test of ggml
#344 by lix19937 was closed Jul 14, 2023 updated Jul 14, 2023
1
compilation broken with cuda
#379 by znsoftm was closed Jul 14, 2023 updated Jul 14, 2023
1
Why add 1024*1024 to ctx_size
#387 by Metal-joker was closed Jul 17, 2023 updated Jul 17, 2023
2
Inference broken with starcoderplus-guanaco-gpt4.ggmlv1.q8_0.bin since 43ffec5 bug Something isn't working
#378 by tim-janik was closed Jul 14, 2023 updated Jul 17, 2023
5
42221 segmentation fault (core dumped) ./mpt
#404 by acheong08 was closed Jul 22, 2023 updated Jul 22, 2023
18
Using Accelerate for vector scale enhancement New feature or request good first issue Good for newcomers
#193 by philipturner was closed Jul 23, 2023 updated Jul 23, 2023
1
9
minor issue: segmentation fault bin/starcoder --seed bug Something isn't working good first issue Good for newcomers
#331 by micsthepick was closed Jul 23, 2023 updated Jul 23, 2023
1
Odd behaviour with GPT2 after bfc6d42 bug Something isn't working
#385 by smspillaz was closed Jul 14, 2023 updated Jul 23, 2023
1
4
ggml : add macros for accessing tensors to reduce code duplication good first issue Good for newcomers refactoring Refactoring
#292 by ggerganov was closed Jul 23, 2023 updated Jul 23, 2023
@goerch
7
ggml : improve API to allow allocating compute graphs on the heap enhancement New feature or request good first issue Good for newcomers
#299 by ggerganov was closed Jul 26, 2023 updated Jul 26, 2023
1
@slaren
9
Do we have plan to support OPT model?
#413 by YixinSong-e was closed Jul 27, 2023 updated Jul 27, 2023
ggml : improve memory management refactoring Refactoring
#288 by ggerganov was closed Jul 30, 2023 updated Jul 30, 2023
1
3
ggml : improve custom operator support enhancement New feature or request good first issue Good for newcomers refactoring Refactoring
#294 by ggerganov was closed Aug 1, 2023 updated Aug 1, 2023
1
4
Support Donut model
#81 by metalwhale was closed Aug 5, 2023 updated Aug 5, 2023
Add a way to change the number of openblas threads in ggml
#452 by klosax was closed Aug 15, 2023 updated Aug 15, 2023
3
Can't run replit-code-instruct-glaive.ggmlv1.q8_0
#453 by Jipok was closed Aug 16, 2023 updated Aug 16, 2023
3
Are there plans to develop CONV_2D? this is also a VIP
#106 by Rane2021 was closed Aug 18, 2023 updated Aug 18, 2023
7
ggml : add broadcast support for BLAS ggml_mul_mat() enhancement New feature or request good first issue Good for newcomers
#460 by ggerganov was closed Aug 21, 2023 updated Aug 21, 2023
1
@ggerganov
GGML_ASSERT: /Users/liu/ggml/src/ggml.c:10798: ne02 == ne12 zsh: abort ./bin/sam -t 16 -i ../image.jpeg -m ../examples/sam/ggml-model-f16.bin
#459 by bccw2021 was closed Aug 21, 2023 updated Aug 21, 2023
3
[Question] Would "Code Llama" be supported out of the box?
#474 by akawrykow was closed Aug 24, 2023 updated Aug 24, 2023
1
GGML GPT-2 consistently dies at around 825 tokens with: ggml_new_object: not enough space in the context's memory pool
#480 by rmc135 was closed Aug 28, 2023 updated Aug 28, 2023
1
1
Some Issues with mul_mat (at least on small matrices)
#478 by joshuadahlunr was closed Aug 29, 2023 updated Aug 29, 2023
4
linesearch_backtracking has confusing logic bug Something isn't working
#501 by cebtenzzre was closed Sep 2, 2023 updated Sep 2, 2023
1
ProTip! Updated in the last three days: updated:>2024-07-02.