Skip to content

Pull requests: ROCm/FlyDSL

New pull request New
24 Open 473 Closed
24 Open 473 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

Use i64 dynamic tensor shapes
#557 opened May 25, 2026 by coderfeli Collaborator Loading…
[Enh] Improve type closure for primitive func
#552 opened May 21, 2026 by sjfeng1999 Collaborator Loading…
1 task
4
[Feat] Align quant and fused layernorm kernels with aiter/triton
#549 opened May 20, 2026 by cschenjunlin Contributor Loading…
3 tasks
3
ci: add amd-ci-job-monitor for runner fleet reporting
#543 opened May 19, 2026 by amdfaa Loading…
6
[Feat] Add FlyDSL MoE sorting kernel
#540 opened May 18, 2026 by amd-weisun Contributor Loading…
31
[gfx1250] Fix cluster launch detection and silent fallback bug Something isn't working
#532 opened May 15, 2026 by aoli26 Contributor • Draft
1 task done
11
[Feature]: support dynamic while
#531 opened May 15, 2026 by xudoyuan Contributor • Draft
1 task
fix: backport manylinux_2_28 wheel build to v0.1.4 (post1 release)
#528 opened May 15, 2026 by kiran-thumma Collaborator • Draft
5 tasks
1
[Feat] Intranode Dispatch&Combine Kernel
#522 opened May 14, 2026 by yanboshao Contributor • Draft
1 task
1
[Optimization]: Replace 'scf.if' with 'arith.select' for visit_ifExp
#512 opened May 12, 2026 by xudoyuan Contributor • Draft
1 task
blockscale code gfx1250 (WIP)
#487 opened May 8, 2026 by omuhamma • Draft
1 task
@omuhamma
fix: handle co_freevars mismatch in ASTRewriter for closure kernels
#474 opened May 6, 2026 by ZJLi2013 Loading…
2 tasks
11
add gfx950 16x16x64 I8 MFMA support to MoE 2-stage GEMM
#461 opened Apr 30, 2026 by yadaish Collaborator • Draft
1 task
Adds Grouped and Batched GEMM kernels with blockscaling matching DeepGEMM API
#433 opened Apr 23, 2026 by aryaman-gupta Loading…
4 tasks done
12
Add A16W4 MoE GEMM stage2 kernel (BF16 activations x MXFP4 weights)
#431 opened Apr 23, 2026 by apicciau Loading…
1 task
@apicciau
9
Add RDNA4 MoE WMMA kernel path
#430 opened Apr 23, 2026 by vivienfanghuagood Collaborator • Draft
Kefan.cao/fix universal copy
#429 opened Apr 23, 2026 by kefan203 Contributor Loading…
1 task
4
Add BF16xFP4 MoE GEMM stage1 kernel
#424 opened Apr 21, 2026 by apicciau • Draft
1 task
Pr/a16wi4 group splitk
#420 opened Apr 21, 2026 by yadaish Collaborator • Draft
1 task
[Kernel][MI350] GDR prefill K5 vk implementation
#405 opened Apr 16, 2026 by huizzhan • Draft
1 task
gemm a16w16 flydsl implementation (WIP)
#401 opened Apr 14, 2026 by omuhamma • Draft
1 task
@omuhamma
Add initial Windows support
#395 opened Apr 13, 2026 by 0xDELUXA • Draft
1 task done
2
Add hgemm_splitk+allreduce prologue/epilogue fusion kernels
#354 opened Apr 7, 2026 by xytpai Contributor • Draft
[Feature] Add JAX integration for FlyDSL kernels
#257 opened Mar 21, 2026 by wenchenvincent Loading…
1 task done
11
ProTip! Add no:assignee to see everything that’s not assigned.