Skip to content

Pull requests: intel/auto-round

New pull request New
36 Open 1,422 Closed
36 Open 1,422 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

refine awq, bugfix WIP
#2115 opened Jul 31, 2026 by WeiweiZhang1 Contributor Loading…
4 tasks
refine eval, add more option
#2114 opened Jul 31, 2026 by WeiweiZhang1 Contributor Loading…
4 tasks
Optimize INT4 MoE prefill/decode (sym) XPU kernels with dedicated w4a16 tiling
#2111 opened Jul 31, 2026 by Copilot AI • Draft
1 of 4 tasks
@a32543254
Add python 3.14t compatibility tests
#2110 opened Jul 31, 2026 by XuehaoSun Contributor Loading…
2
ark.moe: switch auto dispatch to total-token threshold + env override
#2108 opened Jul 31, 2026 by Copilot AI • 2/2 Loading…
2 of 4 tasks
@a32543254
Automatically select calibration datasets for code models
#2107 opened Jul 30, 2026 by changwangss Contributor Loading…
4 tasks
15
Fix AutoRound gradients for Kimi-VL routed experts
#2097 opened Jul 28, 2026 by lesj0610 • Draft
Support SVDQuant
#2095 opened Jul 28, 2026 by changwangss Contributor Loading…
4 tasks
4
add rotation ut for xpu.
#2094 opened Jul 27, 2026 by lkk12014402 Contributor Loading…
2
Migrate cpu sdpa from NS flash attn
#2092 opened Jul 27, 2026 by jijiaz Loading…
2 of 5 tasks
Opt the moe performance
#2090 opened Jul 27, 2026 by a32543254 Contributor • 1/2 Loading…
4 tasks
11
add blockwise rotation.
#2087 opened Jul 24, 2026 by lkk12014402 Contributor Loading…
6
perf: N-based tile selection for XPU bf16/fp16 MoE grouped GEMM
#2079 opened Jul 23, 2026 by Copilot AI • Draft
1 of 4 tasks
@a32543254
support fused MoE quantization and export for GGUF format
#2072 opened Jul 21, 2026 by n1ck-guo Contributor Loading…
4 tasks
20
Allow non-MLLM calibration datasets when not quantizing vision
#2065 opened Jul 19, 2026 by aquilarubra Contributor Loading…
3
Stream targeted block re-quantization's calibration pass
#2064 opened Jul 19, 2026 by aquilarubra Contributor Loading…
Add crash/resume support for tuning runs (AR_RESUME_DIR)
#2062 opened Jul 19, 2026 by aquilarubra Contributor Loading…
Refator UT and improve code coverage
#2057 opened Jul 16, 2026 by lvliang-intel Contributor Loading…
2 of 4 tasks
4
feat: add per-head fp8 kv attention calibration
#2044 opened Jul 10, 2026 by zeel2104 Loading…
2 of 4 tasks
10
feat: Support world model Cosmos3
#2040 opened Jul 10, 2026 by lvliang-intel Contributor Loading…
3 of 4 tasks
6
fix the int4 ark test
#2038 opened Jul 10, 2026 by a32543254 Contributor Loading…
4 tasks
2
test: stabilize flaky int4-sym fp16 MoE prefill accuracy test
#2033 opened Jul 9, 2026 by Copilot AI • Draft
4 tasks done
@a32543254
44
[WIP]refine quantizer
#2031 opened Jul 9, 2026 by wenhuach21 Contributor Loading…
4 tasks
1
Enhance CI pipeline and unit tests for AI failure analysis WIP
#2029 opened Jul 9, 2026 by chensuyue Contributor Loading…
Implementing bandwidth metrics for performance tests
#2020 opened Jul 8, 2026 by Copilot AI • Draft
@a32543254
1
ProTip! Mix and match filters to narrow down what you’re looking for.