Skip to content

Pull requests: ROCm/triton

New pull request New
66 Open 663 Closed
66 Open 663 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

Insert iglp(10) in computer cluster as the marker for better instruction interleaving
#820 opened May 31, 2025 by zhanglx13 Loading…
1
Add bf16 gemm pingpong with num_stages=3
#818 opened May 30, 2025 by jungpark-mlir Loading…
6
Bypass LDS for scale B operand for skinny gemms
#817 opened May 29, 2025 by plognjen Loading…
5
[DO NOT MERGE!!!] Introduce tilesPerWarp parameter, scale preshuffling and bypassingLDS
#809 opened May 23, 2025 by plognjen • Draft
2
[DRAFT] Shared/aggregate load
#804 opened May 21, 2025 by alefimov-amd • Draft
[AMD] Improve Scheduling for Async BF16 GEMM
#802 opened May 21, 2025 by raikonenfnu Loading…
7 tasks
1
add predicate mask for atomic_rmw ops
#799 opened May 19, 2025 by scxiao Loading…
4 of 7 tasks
[AMD] added slicing ttg.async_copy_global_to_local
#797 opened May 15, 2025 by ravil-mobile Loading…
31
Enchanged rocm-triton-prof.py; regex, config-yaml file
#793 opened May 7, 2025 by ravil-mobile Loading…
1
[AMD] Added canonicalization pattern to propagate DotOp attrs
#792 opened May 7, 2025 by ravil-mobile Loading…
4
[AMD] Added Refine-Reschedule hint for rescheduling
#791 opened May 5, 2025 by ravil-mobile Loading…
1
Shaoclee/compare ck
#788 opened May 2, 2025 by k50112113 Loading…
5 of 7 tasks
[DRAFT] [RefineOps] Emit tensors in non-redundant layout for elementwise ops
#785 opened Apr 28, 2025 by binarman • Draft
9
[WIP] [StreamK]
#782 opened Apr 28, 2025 by zhanglx13 • Draft
8
[AMD] Added bufferOps refinement
#776 opened Apr 14, 2025 by ravil-mobile Loading…
14
update scale dot assertion in plot_layout.py
#774 opened Apr 10, 2025 by jtang10 Loading…
Tjactions security issue
#773 opened Apr 3, 2025 by Cemberk Loading…
Update FlashAttention transV scripts
#766 opened Mar 21, 2025 by binarman Loading…
Add v2 test to paged_attention_decode
#764 opened Mar 20, 2025 by rahulbatra85 Loading…
1
MLA prefill, forward_normal benchmark
#750 opened Mar 7, 2025 by Chi-Chu319 Loading…
@Chi-Chu319
Cap warp count to 16 for devices with warp size 64
#747 opened Mar 5, 2025 by schung-amd • Draft
4 of 7 tasks
[AMD][RFC][DO-NOT-MERGE] Named-barrier using LDS
#720 opened Feb 4, 2025 by karthik-man • Draft
Attempt to unify perf kernel and AOTriton's kernel.
#716 opened Jan 29, 2025 by xinyazhang Loading…
10
Add int4 quantization support to MoE
#715 opened Jan 28, 2025 by rahulbatra85 Loading…
19
Multihead latent attention
#712 opened Jan 24, 2025 by juuso-oskari • Draft
@juuso-oskari
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.