Skip to content

Pull requests: tile-ai/tilelang

New pull request New
22 Open 1,438 Closed
22 Open 1,438 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

[example] use alloc_global in split-kv decode kernel
#1991 opened Mar 28, 2026 by botbw Loading…
2
[BugFix] Fix auto vectorization for binary operations after wider copy instructions
#1986 opened Mar 27, 2026 by Achazwl Loading…
4
[Feature] Introduce tile schedule
#1983 opened Mar 27, 2026 by Rachmanino • Draft
2
[Enhancement] Use atomic directory rename for cache writes
#1982 opened Mar 27, 2026 by LeiWang1999 Loading…
2 of 3 tasks
4
[BugFix] Add missing fences in GEMM SM100 examples and canonicalize the order of blockIdx
#1980 opened Mar 26, 2026 by Rachmanino Loading…
2
[Feature] Batched AllReduce for better T.reduce performance
#1976 opened Mar 26, 2026 by kurisu6912 Loading…
3 tasks done
1
8
[Bugfix] Fix CuTeDSL autotune cache invalid ELF header (#1967)
#1972 opened Mar 25, 2026 by kurisu6912 Loading…
3 tasks done
1
5
Introduce T.deallocate_tmem and T.transpose
#1971 opened Mar 25, 2026 by LeiWang1999 Loading…
8
[WIP][Feature] Introduce CUDARunner
#1970 opened Mar 24, 2026 by SiriusNEO • Draft
2
[AMD] [Radeon] Support flash attention bwd on rdna4 GPU
#1965 opened Mar 23, 2026 by zhangnju Loading…
11
Nan propagation option for bf16 and half16
#1958 opened Mar 21, 2026 by haoran35-jpg Loading…
12
[Feature] Block-scaled GEMM support for MXFP8 on Blackwell
#1945 opened Mar 18, 2026 by Rachmanino Loading…
25
[WIP][Feature]: add NV FP4 GEMM support for SM100 & SM120
#1918 opened Mar 9, 2026 by Hale423 Loading…
23
[Feature] Add T.copy_cluster to support TMA multicast and SM-to-SM cluster copy
#1908 opened Mar 7, 2026 by He-Jingkai Loading…
68
Add Metal T.gemm_v2 using simdgroup_multiply_accumulate
#1869 opened Feb 23, 2026 by oraluben Loading…
15
[Feature] Add TIR builtins for warp-level vote and block-level predicate sync
#1858 opened Feb 18, 2026 by sepcnt • Draft
1
9
support dlcompiler
#1843 opened Feb 12, 2026 by zhaochaoxing • Draft
2
[MISC] Fixed the image display issue under different themes.
#1838 opened Feb 11, 2026 by 1195343015 Loading…
5
[Feature] Introduce auto warp specialize & scheduling
#1831 opened Feb 10, 2026 by silentCoder-dev Loading…
45
[Transform] Split instruction inference from LowerTileOp to InferInstructions
#1808 opened Feb 7, 2026 by Rachmanino • Draft
12
feat(commonir): add commonir abstract backend
#1754 opened Jan 29, 2026 by CokeDong • Draft
24
[DCU] Support the deployment and operation of tilelang on the Hygon DCU backend
#1145 opened Oct 28, 2025 by Lukinon • Draft
31
ProTip! Exclude everything labeled bug with -label:bug.