Skip to content

Pull requests: ROCm/aiter

New pull request New
502 Open 3,816 Closed
502 Open 3,816 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(moe): consume prepared stage1 activation scales
#4762 opened Aug 14, 2026 by JohnQinAMD Contributor Loading…
6
[PERF] Optimize Triton unified attention prefill and decode
#4761 opened Aug 14, 2026 by vorapolsiloai • Draft
5 of 7 tasks
1
[gfx1250][FlyDSL] Update a8w8 gemm tuned config
#4760 opened Aug 14, 2026 by aoli26 Contributor Loading…
1 task
2
Add full 16-tier Qwen3-VL FP4 MoE tuned config for gfx950
#4759 opened Aug 14, 2026 by johannes-graner Contributor Loading…
1 task
4
[Gluon][MLA] Deeper async-copy pipeline in the bh16 stage-1 decode loop
#4758 opened Aug 14, 2026 by amd-ethany • Draft
1 task done
1
[detorch] remove vestigial py_itfs_common.h includes (non-CK); top_k_per_row now torch-free
#4756 opened Aug 14, 2026 by amd-ruitang3 Contributor Loading…
1
[Opus MoE] Unify A8W4 metadata and runtime dispatch
#4755 opened Aug 14, 2026 by yifehuan Contributor Loading…
1 task
1
[Bugfix] Disable cpp_itfs sampling on ROCm 10
#4754 opened Aug 14, 2026 by fsx950223 Contributor Loading…
3 tasks done
4
fix: LL proto ar dispatch
#4753 opened Aug 14, 2026 by TennyWang1223 Contributor Loading…
1 task
1
ci: centralize PyTorch test image config
#4750 opened Aug 14, 2026 by gyohuangxin Member Loading…
3
Alizaidy/bf16 gemm tuning 081426
#4749 opened Aug 14, 2026 by azaidy Contributor Loading…
1
(WIP) [gfx1250] fix(asm gemm): add a_preshuffle=0 f4gemm & f8gemm, fix corner case support and enhance ut do-not-merge
#4748 opened Aug 14, 2026 by dbyoung18 Contributor Loading…
1
Fp8 mxscale bmm bpreshuffle opt
#4747 opened Aug 14, 2026 by yzhou103 Contributor • Draft
1 task
1
fix(rope): tolerate missing original_max_position_embeddings
#4742 opened Aug 14, 2026 by lizamd Loading…
3 tasks done
1
[FlyDSL] Add gfx950 Kimi Delta Attention prefill kernel
#4741 opened Aug 13, 2026 by amd-wsung102 Loading…
1 task done
1
Fix/gfx1201 bf16 g1u1 small m moe
#4740 opened Aug 13, 2026 by keneoneth • Draft
1 task
1
[Misc] Harden AITER_ASM_DIR code-object loading
#4739 opened Aug 13, 2026 by fjankovi • Draft
4 of 6 tasks
1
[TRITON] Make RNG deterministic in KV cache unit test ci:triton-300x ci:triton-355
#4738 opened Aug 13, 2026 by brunomazzottiamd Contributor Loading…
1 task done
@brunomazzottiamd
1
[CI] PR auto tag
#4737 opened Aug 13, 2026 by Boss2002n Contributor Loading…
4
Replace block_ptr in HSTU attn kernel
#4736 opened Aug 13, 2026 by scxiao Contributor Loading…
1 task
1
hd256 fp8 attention perf improvement
#4733 opened Aug 13, 2026 by JohnNikolay84 Contributor Loading…
1 task
@JohnNikolay84 @vstakhov-amd
1
[FLYDSL] Support prefill GDN K5 fp32 chunk states
#4732 opened Aug 13, 2026 by huizzhan Contributor Loading…
3 tasks done
1
Fix fp8 mqa for dsv4 on gfx1250
#4731 opened Aug 13, 2026 by HaonanWang98 Contributor Loading…
1 task
1
moe gemm optimization
#4730 opened Aug 13, 2026 by yadaish Contributor Loading…
1 task
1
Fuse block-banking cat into attn_res_gate via close_block/WRITE_BLOCK…
#4726 opened Aug 13, 2026 by yanxuer-999 Contributor Loading…
1 task
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.