Skip to content

Pull requests: intel/neural-compressor

New pull request New
11 Open 1,934 Closed
11 Open 1,934 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(pytorch): Rename layer_scale parameter to avoid quantization error
#2172 opened Apr 14, 2025 by ved1beta Loading…
1
suit transformers>=4.51
#2171 opened Apr 14, 2025 by xin3he Loading…
3
k quant
#2169 opened Apr 10, 2025 by jiafatom Loading…
13
Reset accelerator when INC_TARGET_DEVICE is set in code
#2168 opened Apr 10, 2025 by Kaihui-intel Loading…
3
[pre-commit.ci] pre-commit autoupdate
#2166 opened Apr 7, 2025 by pre-commit-ci bot Loading…
1
Add support for optimum-habana deepseek v3/r1 fp8 quantization
#2164 opened Apr 4, 2025 by skavulya • Draft
[SW-219134]: Remove legacy import in init.
#2157 opened Mar 31, 2025 by feng-intel Loading…
2
Recover PatchedVLLMKVCache
#2156 opened Mar 28, 2025 by mengniwang95 Loading…
Add a feature of UniformQDQ - support CV/NLP model's OPs, includingConv, DepthwiseConv2D, MatMul, etc. Additional op support be added upon request.
#2155 opened Mar 27, 2025 by qgao007 Loading…
11
R1 woq self-review won't merge
#2148 opened Mar 21, 2025 by yiliu30 • Draft
Add update_g_idx flag for setting qweight&g_idx related to ipex-xpu v2.7 Waiting for ipex gpu v2.7 to be ready
#2143 opened Mar 10, 2025 by Kaihui-intel Loading…
5
ProTip! What’s not been updated in a month: updated:<2025-03-14.