-
Notifications
You must be signed in to change notification settings - Fork 710
Pull requests: tile-ai/tilelang
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[CUDA] Bridge half-style math intrinsics for 16-bit CUTLASS types
#3077
opened Aug 24, 2026 by
Chennesxu
Contributor
Loading…
[Enhancement] Reject fragment slicing & Allow shared memory slicing in reduce
#3076
opened Aug 24, 2026 by
KellyFrog
Collaborator
Loading…
[BugFix][Transform] Guard short symbolic software-pipeline epilogues
#3072
opened Aug 23, 2026 by
3402956340
Loading…
[BugFix][Transform] Avoid int32 overflow in vector analysis
#3066
opened Aug 22, 2026 by
kobecai
Loading…
5 tasks done
[Bugfix] Fix non-divisible nested modulo simplification
#3065
opened Aug 22, 2026 by
haoyang9804
Loading…
[BugFix][Layout] Accept Python int coalesced width annotations
#3064
opened Aug 22, 2026 by
kobecai
Loading…
[BugFix][Layout] Fix parallel layout undercoverage
#3063
opened Aug 21, 2026 by
haoyang9804
Loading…
[DO NOT REVIEW] [Feature] [CUDA] Role-based warp specialization scheduler
#3059
opened Aug 20, 2026 by
Yongqi-Zhuo
Collaborator
•
Draft
[BugFix] Preserve buffer-loaded guard dependencies in pipelines
#3052
opened Aug 19, 2026 by
kobecai
Loading…
4 tasks done
[Language] Unify contiguous stride construction using a single implem…
#3016
opened Aug 16, 2026 by
jjppp
Contributor
Loading…
[BugFix][Hopper][Blackwell] Read the WGMMA/UMMA K-panel stride from the layout instead of the operand extent
#2965
opened Aug 14, 2026 by
bigSheep123
Contributor
Loading…
[BugFix][CUDA] Restore cp.async for predicated zero-fill copies
#2926
opened Aug 9, 2026 by
hebo1221
Loading…
[BugFix][CPU] Compute scalar GEMM products in accum dtype instead of input dtype
#2917
opened Aug 7, 2026 by
Dino1844
Loading…
[ROCm] Scalarize vectorizable calls in vector Select lowering
#2915
opened Aug 7, 2026 by
morluto
Contributor
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-08-21.