Skip to content

Pull requests: ROCm/aiter

New pull request New
281 Open 2,442 Closed
281 Open 2,442 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

mla/gather_kv_b_proj: handle unquantized kv_b_proj weight (kv_proj_scale=None) ci:all
#3006 opened May 2, 2026 by kzjeef Loading…
1
[Silo] Bulk merge: kernel fixes and features (SplitK, MoE fixes, Qwen3-Next, pa_mqa OOB)
#3005 opened May 1, 2026 by sunway513 Collaborator Loading…
3 tasks
10
Add HipKittens based nhead=32 MLA kernel on MI35x / gfx950
#3003 opened May 1, 2026 by hubertlu-tw Contributor Loading…
8 of 9 tasks
1
ci(nightly): fix wheel/image ABI mismatch + 0-test false-pass (run 25202894144)
#3002 opened May 1, 2026 by sunway513 Collaborator Loading…
1
Remove sorting for fmoe
#3001 opened May 1, 2026 by JohnNikolay84 Contributor • Draft
1 task
@JohnNikolay84
1
Replace QH16 bf16 kernel with a new one that does not use ptr_RP
#2999 opened May 1, 2026 by JohnNikolay84 Contributor Loading…
1 task
@JohnNikolay84
1
Dsv4 sparse indexer
#2998 opened May 1, 2026 by Oseltamivir Loading…
1 task done
5
mla: refuse page_size > 1 on bf16 decode-stage1 kernel (no _ps variant shipped)
#2997 opened May 1, 2026 by kzjeef Loading…
4 tasks done
3
add topk_softplus kernel
#2995 opened May 1, 2026 by yzhou103 Contributor Loading…
1 task
5
[Gluon]: Gluon kernel for mxfp4 quant
#2994 opened May 1, 2026 by NimitPtl • Draft
1 task
13
[FLYDSL] Extend gfx1201 FA backend coverage to Wan2.2 TI2V-5B shapes (H=24, D=128)
#2990 opened May 1, 2026 by sunway513 Collaborator Loading…
4 of 6 tasks
ci: make Standard Tests resilient to PRs missing install_triton.sh
#2985 opened Apr 30, 2026 by sunway513 Collaborator Loading…
6
[TRITON] Split test_mha.py into smaller test files ci:triton-300x ci:triton-355 enhancement New feature or request triton
#2984 opened Apr 30, 2026 by brunomazzottiamd Contributor Loading…
1 task done
@brunomazzottiamd
4
[MLA] Fix nhead=32 non-persistent decode crash on gfx950
#2983 opened Apr 30, 2026 by frida-andersson Contributor Loading…
2
Add MiniMax M25 FMoE tunings
#2982 opened Apr 30, 2026 by akii96 Contributor • Draft
1
[configs] Add MI355X tuned GEMM and FMoE configs for DeepSeek-V3.2
#2981 opened Apr 30, 2026 by frida-andersson Contributor Loading…
2
Add MiniMax M25 A8W8 blockscale GEMM tunings
#2979 opened Apr 30, 2026 by akii96 Contributor • Draft
2
CI: retry docker pulls in workflow image downloads ci:all
#2977 opened Apr 30, 2026 by gyohuangxin Member Loading…
3 tasks done
3
mxfp4 quantize kernel
#2976 opened Apr 30, 2026 by amd-yilizhao Contributor Loading…
1
[Moe_sorting_opus] refactor ci:all
#2974 opened Apr 30, 2026 by amd-ruitang3 Contributor Loading…
1 task
6
add swiglu a4w4 moe path for gpt-oss model
#2972 opened Apr 30, 2026 by XiaobingSuper Contributor • Draft
1 task
1
[Triton] [gfx1250] GEMM A16W16 Kernel
#2971 opened Apr 29, 2026 by azaidy Contributor • Draft
1
[FLYDSL] Add gfx1201 (RDNA4) flash_attn_func backend
#2969 opened Apr 29, 2026 by sunway513 Collaborator Loading…
18
[GFX1250] Add Triton TDM to MoE Metadata kernels
#2968 opened Apr 29, 2026 by nsusanto Contributor Loading…
2
[TRITON] mHC: Apply post-stream and res-stream mixing
#2967 opened Apr 29, 2026 by waqahmed-amd-fi • Draft
1 task
@waqahmed-amd-fi
1
ProTip! Filter pull requests by the default branch with base:main.