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
220 Open 532 Closed
220 Open 532 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

User defined operation
#836 opened May 24, 2024 by Francis235
2
issues about YaRN
#835 opened May 24, 2024 by foldl
1
Completion of error handling
#834 opened May 23, 2024 by elfring
ggml how to compute depthwise conv
#833 opened May 21, 2024 by Francis235
GGML Fragmentation Issue
#830 opened May 19, 2024 by zhouwg
GGML_MAX_NAME is too small.
#825 opened May 16, 2024 by IntptrMax
1
GGML_CUDA default to ON if CUDA is available.
#817 opened May 11, 2024 by xth Loading…
added comment explaining group norm behavior in ggml.h
#813 opened May 4, 2024 by balisujohn Loading…
3
ggml vs Qualcomm SNPE inference engine on qualcomm soc
#809 opened Apr 30, 2024 by Francis235
feat : add col2im kernels
#808 opened Apr 29, 2024 by PABannier • Draft
1 of 4 tasks
1
Behaviour Mismatch between ggml_opt in Native Program and WASM
#807 opened Apr 29, 2024 by saraalrawi
add way to compile ggml with intel mkl
#804 opened Apr 23, 2024 by kannon92 Loading…
6
Behavior mismatch between PyTorch GroupNorm and ggml_group_norm
#803 opened Apr 21, 2024 by balisujohn
5
The library crashes with illegal instructions when the F16C extension isn't supported, please use google's cpu_features library and fail gracefully in such case
#799 opened Apr 17, 2024 by yurivict
GGUF quantization meta-data format
#797 opened Apr 14, 2024 by mobicham
2
any support for MUL_MAT operation in unsupported GPU feature? (macos intel/amd gpu)
#796 opened Apr 14, 2024 by posojeg
2
is there any plan to complete the implementation of use supports_op to check if the backend supports the op?
#795 opened Apr 13, 2024 by zhouwg
Magic number in example
#791 opened Apr 8, 2024 by wilderfield
7
backend: remove duplicate backend typedefs
#785 opened Apr 5, 2024 by danbev Loading…
backend: remove unused macro
#783 opened Apr 4, 2024 by danbev Loading…
Standardized prompting metadata
#774 opened Mar 27, 2024 by MoonRide303
3
test-timestep_embedding _sometimes_ fails with ptrace: Operation not permitted. [opencl-clover, gfx1103] (with gdb backtrace.)
#772 opened Mar 27, 2024 by dreirund
Quant and Dequant operators
#769 opened Mar 21, 2024 by sankalpdayal
Why perform such operations on k and v as shown in the above diagram?
#766 opened Mar 16, 2024 by EveningLin
1
How to deploy my own model using ggml framework
#762 opened Mar 12, 2024 by Francis235
3
ProTip! Adding no:label will show everything without a label.