Skip to content

Pull requests: huggingface/optimum-quanto

New pull request New
Clear current search query, filters, and sorts
1 Open 218 Closed
1 Open 218 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix(library): Propagate upstream Marlin kernel fix Stale
#366 by ahadnagy was closed Jan 29, 2025 Loading… updated Jan 29, 2025
3 of 4 tasks
1
5
fix(library): only compile CUDA extension on Linux
#365 by dacorvo was merged Jan 10, 2025 Loading… updated Jan 10, 2025
1
Add repr for QuantizedTransformersModel
#357 by imba-tjd was merged Nov 25, 2024 Loading… updated Nov 25, 2024
2 of 4 tasks
1
1
[tests] enable testing for xpu
#344 by faaany was closed Nov 12, 2024 Loading… updated Nov 13, 2024
2 of 4 tasks
8
[tests] enable test_weight_qbits_tensor_linear_cuda on xpu devices
#345 by faaany was closed Nov 12, 2024 Loading… updated Nov 13, 2024
2 of 4 tasks
2
enable qbitstensor test on xpu
#350 by dacorvo was merged Nov 12, 2024 Loading… updated Nov 12, 2024
[tests] enable testing for xpu (rebased)
#349 by dacorvo was merged Nov 12, 2024 Loading… updated Nov 12, 2024
Support QLayerNorm without weights
#341 by dacorvo was merged Oct 29, 2024 Loading… updated Oct 29, 2024
1
Add support for Marlin fp16/fp8 kernel (refactored)
#296 by dacorvo was merged Aug 28, 2024 Loading… updated Oct 24, 2024
5
fix: use reshape instead of view
#338 by dacorvo was merged Oct 24, 2024 Loading… updated Oct 24, 2024
1
Add marlin int4 kernel
#333 by dacorvo was merged Oct 10, 2024 Loading… updated Oct 10, 2024
Fixed Sometimes the dtype of the model is incorrect Stale
#301 by balala8 was closed Oct 10, 2024 Loading… updated Oct 10, 2024
2 of 4 tasks
10
Switched linters, black -> ruff
#334 by ishandeva was merged Oct 8, 2024 Loading… updated Oct 8, 2024
3 of 4 tasks
15
feat: add HIP support Stale
#280 by Disty0 was closed Oct 4, 2024 Loading… updated Oct 4, 2024
3 tasks
7
Add hip support
#330 by dacorvo was merged Oct 4, 2024 Loading… updated Oct 4, 2024
Refactor extensions
#329 by dacorvo was merged Oct 4, 2024 Loading… updated Oct 4, 2024
Remove overheads in library
#328 by dacorvo was merged Oct 3, 2024 Loading… updated Oct 3, 2024
Fix lumina
#326 by dacorvo was merged Oct 1, 2024 Loading… updated Oct 1, 2024
1
Fix missing call in QuantizedTransformersModel
#325 by dacorvo was merged Sep 30, 2024 Loading… updated Sep 30, 2024
refactor(library): reduce overhead in marlin op
#323 by dacorvo was merged Sep 30, 2024 Loading… updated Sep 30, 2024
Add marlin int4 kernel
#315 by dacorvo was closed Sep 27, 2024 • Draft updated Sep 27, 2024
1
Ci move
#321 by glegendre01 was merged Sep 27, 2024 Loading… updated Sep 27, 2024
4 tasks
1
Stricter optimized tensor tests
#320 by dacorvo was merged Sep 26, 2024 Loading… updated Sep 26, 2024
chore: minimal python version is 3.9
#318 by dacorvo was merged Sep 25, 2024 Loading… updated Sep 25, 2024
Refactor AWQ gemm
#317 by dacorvo was merged Sep 25, 2024 Loading… updated Sep 25, 2024
ProTip! no:milestone will show everything without a milestone.