Skip to content

Pull requests: intel/auto-round

New pull request New
26 Open 955 Closed
26 Open 955 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

feat: handle per-tensor FP8 dequantization for Devstral models
#1356 opened Jan 27, 2026 by SwekeR-463 Loading…
4 of 9 tasks
support qwen3 moe patch
#1354 opened Jan 27, 2026 by wenhuach21 Loading…
9 tasks
8
enable xpu test
#1352 opened Jan 27, 2026 by chensuyue Loading…
9 tasks
1
Chinesization
#1350 opened Jan 27, 2026 by ZaneMark Loading…
2 of 9 tasks
support hadamard transform for mxfp4 with rtn or autoround method.
#1349 opened Jan 27, 2026 by lkk12014402 Loading… 0.10.0
27
Refactor FP8 dequantization and detection using registry pattern
#1348 opened Jan 27, 2026 by scopophobic Loading…
5 tasks done
1
Optimize CPU RAM peak memory during quantization
#1346 opened Jan 27, 2026 by lvliang-intel • Draft
4 of 9 tasks
2
fix ci
#1344 opened Jan 27, 2026 by XuehaoSun Loading…
9 tasks
1
Fix FP8 MLA vllm-ext
#1343 opened Jan 26, 2026 by yiliu30 Loading…
9 tasks
1
refactor init of compressor
#1339 opened Jan 26, 2026 by n1ck-guo Loading…
1 of 9 tasks
6
rm duplicate args of the quantization extra config
#1334 opened Jan 23, 2026 by WeiweiZhang1 Loading…
1 of 9 tasks
1
Fix cpu ut for transformers v5
#1333 opened Jan 23, 2026 by Kaihui-intel Loading…
1 of 9 tasks
0.10.0
16
add support for w4a16_mixed enhancement New feature or request ready only add when the PR is ready to merge
#1326 opened Jan 23, 2026 by n1ck-guo Loading…
6 of 17 tasks
8
Autoround in vLLM Office Hours documentation Improvements or additions to documentation
#1322 opened Jan 23, 2026 by yiliu30 Loading…
1 of 18 tasks
1
enable glm4_moe_lite quantization & generation
#1321 opened Jan 22, 2026 by WeiweiZhang1 Loading…
3 of 18 tasks
9
Add asym for XPU backend.
#1316 opened Jan 22, 2026 by luoyu-intel • Draft
Update torch to 2.9.1 in CI
#1313 opened Jan 22, 2026 by XuehaoSun Loading…
1
align act_max of experts for qwen3-vl and qwen3-next
#1311 opened Jan 21, 2026 by xin3he Loading…
5
Optimize FP8 layer conversion by skipping weight initialization
#1295 opened Jan 16, 2026 by Copilot AI Loading…
@yiliu30
2
[WIP]Ds v32
#1291 opened Jan 16, 2026 by yiliu30 • Draft
@yiliu30
Robust FP8 layer detection for ignore_layers (#1283)
#1289 opened Jan 15, 2026 by scopophobic Loading…
3
Fix ignore_layers not working for FP8 models
#1286 opened Jan 15, 2026 by Copilot AI Loading…
11 tasks done
@yiliu30
8
[WIP][refactor quanizers][step 1] refactor rtn and tuning
#1278 opened Jan 14, 2026 by n1ck-guo Loading…
3
fix disable_opt_rtn spelling error
#1250 opened Jan 9, 2026 by WeiweiZhang1 Loading…
1
add per-task lm_eval args for exprimental usage
#1017 opened Nov 11, 2025 by WeiweiZhang1 Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.