Skip to content

Pull requests: ROCm/aiter

New pull request New
42 Open 502 Closed
42 Open 502 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

Update dependencies and add backup for unknown hw
#623 opened Jul 7, 2025 by kunaltyagi Loading…
2
Remove seqlen limit on FA fwd kernel
#622 opened Jul 7, 2025 by slippedJim Loading…
Refine ck instance and update a8w8_bpreshuffle_tuned_gemm.csv
#621 opened Jul 7, 2025 by solinzby1 Loading…
enable parallel tuning on CK kernels
#617 opened Jul 7, 2025 by yzhou103 Loading…
@valarLip
[TRITON]: Moe tuning mi350
#610 opened Jul 3, 2025 by Chi-Chu319 Loading…
@juuso-oskari @Chi-Chu319
1
[Triton] DS fused custom ops
#607 opened Jul 2, 2025 by k50112113 Loading…
(Triton] RoPE dev
#606 opened Jul 2, 2025 by k50112113 Loading…
[TRITON] Add Softmax Triton Kernel triton
#605 opened Jul 2, 2025 by lucas-santos-amd Loading…
1
[TRITON]: Fix num_warps typo which was causing performance issues
#604 opened Jul 2, 2025 by valechen Loading…
[TRITON] Refactor Triton RMSNorm and LayerNorm unit tests triton
#598 opened Jul 1, 2025 by lucas-santos-amd Loading…
[TRITON]: Standardize GEMM weight shape to (N, K) and TN memory layout (by default)
#597 opened Jul 1, 2025 by willzhou-amd Loading…
3 tasks done
@willzhou-amd
[TRITON]: add json config and refactor
#595 opened Jun 30, 2025 by rahulbatra85 Loading…
4
[TRITON]: Kernel benchmarking improvements (for op_benchmarks/triton)
#594 opened Jun 30, 2025 by willzhou-amd Loading…
2 of 5 tasks
@willzhou-amd
2
fix moe weight out of range when large expert num
#589 opened Jun 27, 2025 by lalala-sh Loading…
1
adding workflow file
#587 opened Jun 26, 2025 by okakarpa Loading…
add num_kv_splits_indptr to mla for mtp<=4 case for now
#584 opened Jun 26, 2025 by valarLip Loading…
merge moe from 350 launch
#580 opened Jun 25, 2025 by lalala-sh Loading…
@valarLip
10
Zan merge seqlen qk ratio nblock16
#574 opened Jun 24, 2025 by Zzz9990 Loading…
15
[DO NOT MERGE] Testing pipeline changes
#562 opened Jun 20, 2025 by leo-amd Loading…
update gfx950 features for moe
#560 opened Jun 19, 2025 by lalala-sh Loading…
[TRITON] Add LayerNorm Backward Triton Kernels triton
#546 opened Jun 16, 2025 by lucas-santos-amd Loading…
4
Add mha_batch_decode() API
#506 opened Jun 4, 2025 by poyenc • Draft
@poyenc
[TRITON][GFX950] Proton Capability & Metadata for GEMM fp4
#494 opened May 29, 2025 by jtang10 Loading…
Update quant.py
#487 opened May 28, 2025 by Lzy17 Loading…
Add act_first flag in activation op to support flexible input ordering
#478 opened May 26, 2025 by Conless Loading…
1 task done
8
ProTip! What’s not been updated in a month: updated:<2025-06-07.