Skip to content

Pull requests: ROCm/FlyDSL

New pull request New
49 Open 696 Closed
49 Open 696 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

[CI] Make MLIR cache fallback reliable
#897 opened Jul 24, 2026 by Phil-amd Member Loading…
1 of 4 tasks
[Kernel][MI350] Add 8 wave GQA sliding-window attention kernel
#894 opened Jul 23, 2026 by amd-nprotaso Loading…
2
Refactor mxmoe
#892 opened Jul 23, 2026 by coderfeli Collaborator Loading…
[Test] Add gfx1250 WMMA lowering tests for additional dtypes
#891 opened Jul 23, 2026 by AiyyappanMR Loading…
2 of 3 tasks
[Kernel][MI350] Add cache-aware 8-wave BF16/FP16 GEMM
#888 opened Jul 23, 2026 by zhanglx13 • Draft
6 tasks done
gemm: add fp8 per-tensor grouped GEMM forward (M-grouped/MoE)
#887 opened Jul 23, 2026 by kyle-256 Loading…
1 task done
6
Add optional forward LSE output
#886 opened Jul 23, 2026 by AakarshAMD Loading…
MegaMoEV1 on Gfx950 multi-gpu
#876 opened Jul 21, 2026 by GwilliamHu Member Loading…
1 task
a16w16 for gfx1250 on flydsl
#875 opened Jul 20, 2026 by omuhamma Loading…
@omuhamma
[compiler] carry Python containers through dynamic if/for/while/ifexp
#874 opened Jul 20, 2026 by xudoyuan Collaborator Loading…
1 task
[Kernel] Add optimized 4-wave MXFP8 GEMM kernel for gfx950
#872 opened Jul 18, 2026 by aris134 Loading…
1 task done
@aris134
2
[Kernel] Add CDNA SageAttention kernel
#869 opened Jul 16, 2026 by LiuYinfeng01 Loading…
1
[Kernel] fp8 conv3d: 8-wave GEMM pipeline + BIG_IN fix
#860 opened Jul 15, 2026 by jiacao-amd Contributor • Draft
3 tasks
[Perf] Optimize rmsnorm/layernorm
#848 opened Jul 14, 2026 by cschenjunlin Contributor Loading…
1 task
18
Add forward LSE output to FlyDSL flash attention kernels
#844 opened Jul 14, 2026 by amd-wsung102 Contributor Loading…
1 of 2 tasks
10
Add a8w4 kernel for Quark mix-precision
#837 opened Jul 12, 2026 by amd-xiaoyu12 Loading…
1 task
1
Gfx1250 tdm gather scatter
#833 opened Jul 12, 2026 by coderfeli Collaborator Loading…
1 task
[Feature] Extract reusable event-based benchmarking helper
#829 opened Jul 10, 2026 by jhinpan Collaborator • Draft
6 of 7 tasks
[MoE] Add gelu_tanh activation to MoE stage1 GEMM kernels
#823 opened Jul 9, 2026 by jonahbernard Loading…
1 task done
2
[3/5] autotune: add offline config artifacts (#770)
#786 opened Jul 1, 2026 by jhinpan Collaborator Loading…
20
flash_attn_generic: replace raw arith.* FP ops with FlyDSL-typed fast…
#764 opened Jun 29, 2026 by xudoyuan Collaborator • Draft
1 task
1
5
[repro] flash_attn_generic: concise causal-mask loop trips dynamic-if…
#763 opened Jun 29, 2026 by xudoyuan Collaborator • Draft
1 task
FlyDSL gemm_decode: small-M dense GEMM kernels (BF16/FP8/blockscale)
#757 opened Jun 26, 2026 by vedenev-amd • Draft
1 task
@vedenev-amd
1
runtime: hard-fail mgpuModuleLoadJIT on HIP
#748 opened Jun 25, 2026 by fallintoplace Loading…
2
fix tile syntax in divide
#746 opened Jun 25, 2026 by tingqli Contributor Loading…
1 task
3
ProTip! Adding no:label will show everything without a label.