-
Notifications
You must be signed in to change notification settings - Fork 111
Pull requests: ROCm/FlyDSL
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Misc][FlyToROCDL] Bump LLVM to 941a04e6 and adapt gpu.launch_func lowering
#1051
opened Aug 21, 2026 by
Phil-amd
Member
Loading…
[Fix] Restore the fx.maxnumf contract, and keep ninf off the score reductions
#1050
opened Aug 21, 2026 by
JohnQinAMD
Contributor
Loading…
5 tasks done
Add review-flydsl-kernel: legacy-spelling scanner distilled from 479 maintainer comments
#1047
opened Aug 20, 2026 by
jhinpan
Collaborator
Loading…
[Bugfix] Refuse a batch entry the buffer descriptor cannot address
#1045
opened Aug 20, 2026 by
JohnQinAMD
Contributor
Loading…
4 tasks done
[AOT] Add resilient parallel job scheduler
#1038
opened Aug 20, 2026 by
zhiding512
Collaborator
Loading…
3 tasks done
[ROCDL] Lower approximate exp2 to native intrinsic
#1037
opened Aug 19, 2026 by
jhinpan
Collaborator
Loading…
8 tasks done
[Bugfix][Kernel] Fix NaN from the lazy rescale on a wide score range
#1033
opened Aug 19, 2026 by
JohnQinAMD
Contributor
Loading…
5 tasks done
[Kernel] Add dilation, padding_mode and groups to convolution kernel.
#1032
opened Aug 19, 2026 by
amd-nprotaso
Contributor
Loading…
[Skills] Fix silently-ignored frontmatter, de-drift kernel skills and CLAUDE.md
#1027
opened Aug 18, 2026 by
jhinpan
Collaborator
Loading…
[Kernel] Add opt-in autotuning for Softmax
#1022
opened Aug 18, 2026 by
jhinpan
Collaborator
Loading…
3 of 4 tasks
[Bugfix][Kernel] Fix fp8 dense attention: softmax normalisation and an int32 dim overflow
#1020
opened Aug 18, 2026 by
JohnQinAMD
Contributor
Loading…
5 of 6 tasks
[Tools] Add architecture-general ISA resource diff tool
#1015
opened Aug 17, 2026 by
Phil-amd
Member
Loading…
[ROCDL] Add make_tiled_tdm_atom op and tdm_partition
#1013
opened Aug 14, 2026 by
sjfeng1999
Collaborator
Loading…
1 task
[MFMA] Add 16x16x16 bf16/f16 support with fly-fix-bitcast-width pass
#1012
opened Aug 14, 2026 by
RichardChamberlain1
Loading…
1 of 6 tasks
[WIP][Compiler][gfx120] Add modC/reuseA/reuseB to MmaOpGFX1250_WMMAType
WIP
#1001
opened Aug 12, 2026 by
jli-melchior
Collaborator
Loading…
1 task
[WIP][Fix] Fix
lld invocation failed when ROCm is not at the baked-in path
#987
opened Aug 8, 2026 by
jli-melchior
Collaborator
Loading…
1 task
[Kernel] Fix single-accumulator RDNA3 GEMM tiles
#986
opened Aug 8, 2026 by
skyguan92
Contributor
Loading…
[Feat] Add an experimental cuda nvvm backend
#976
opened Aug 6, 2026 by
sjfeng1999
Collaborator
Loading…
1 task
add A4W4 and FP8 P2P transport support to MegaMoE
multi-gpu
#972
opened Aug 6, 2026 by
Yaowu-Xiong
Contributor
Loading…
1 task
[Kernel] Add submanifold sparse 3D convolution (bf16 implicit GEMM, gfx950)
#942
opened Jul 31, 2026 by
jiacao-amd
Contributor
•
Draft
Add flex_attention (score_mod / mask_mod) on the generic flash-attention kernel
#931
opened Jul 30, 2026 by
RichardChamberlain1
•
Draft
3 of 4 tasks
Unify benchmark timing contracts and add calibrated CI gates
#924
opened Jul 30, 2026 by
jhinpan
Collaborator
Loading…
6 tasks done
[DSL] Preserve logical signedness of unsigned integer dtypes
#920
opened Jul 28, 2026 by
Arist12
Contributor
Loading…
6 tasks done
Previous Next
ProTip!
Adding no:label will show everything without a label.