Skip to content

Pull requests: triton-lang/triton

New pull request New
205 Open 12 Closed
205 Open 12 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

[FPSAN] Add support for wgmma in fpsan
#10112 opened Apr 22, 2026 by pawelszczerbuk Contributor Loading…
[AMD][GFX12] Cache modifiers for buffer and async ops
#10109 opened Apr 22, 2026 by alefimov-amd Contributor Loading…
[AMD][gfx1250] Add fused SwiGLU mode to gluon mxfp GEMM example
#10108 opened Apr 22, 2026 by kelesvol Contributor Loading…
[GLUON] shared_atomic_add implementation
#10100 opened Apr 21, 2026 by Jokeren Contributor Loading…
4
Enable PartitionedSharedEncodingAttr in the memdesc_subslice lowering
#10099 opened Apr 21, 2026 by plognjen Contributor Loading…
10
[AMD][gluon] Derive gfx1250 write slot from read phase for membar disjointness
#10088 opened Apr 20, 2026 by jungpark-mlir Contributor Loading…
[Membar] Buffer-index disjointness analysis for multi-buffered shared memory
#10087 opened Apr 20, 2026 by jungpark-mlir Contributor Loading…
16
[GSan] Actually reserve 1PiB of address space
#10084 opened Apr 20, 2026 by peterbell10 Contributor • Draft
1
[WIP] test asan
#10080 opened Apr 20, 2026 by PMylon Contributor • Draft
[build] Materialize nvidia backend include overrides for GSan builds
#10072 opened Apr 19, 2026 by meinie0826 Loading…
5 of 7 tasks
1
[FRONTEND] Validate scale tensor dtype in dot_scaled
#10070 opened Apr 18, 2026 by Chennesxu Loading…
5 of 7 tasks
[NFC] Update ConSan docs and move aux-data comments into Utility.h
#10064 opened Apr 17, 2026 by pawelszczerbuk Contributor Loading…
6
[PROTON] Support perfetto_trace and clean up trace dump code
#10061 opened Apr 17, 2026 by Jokeren Contributor • Draft
[AMD][TDM] Add partial TDM copy support via warp_bases
#10056 opened Apr 16, 2026 by jungpark-mlir Contributor Loading…
13
[FPSAN] Enable FPSan with combined instrumentation modes
#10045 opened Apr 15, 2026 by pawelszczerbuk Contributor Loading…
[AMD] Enable TDM with column major tensors and partitioned encodings
#10044 opened Apr 15, 2026 by plognjen Contributor • Draft
[Triton] Fix LLVMDILocalVariable pass crash with LLVM_EXTRACT_DI_LOCAL_VARIABLES
#10042 opened Apr 15, 2026 by byoshimi-gmail Contributor Loading…
5 of 7 tasks
3
[Backend] Bump to llvm/llvm-project@f0f96c7f
#10041 opened Apr 15, 2026 by antiagainst Member • Draft
[AMD][DRAFT] PC Sampling, wave stall reasonings
#10020 opened Apr 13, 2026 by ZelboK Contributor • Draft
[DNR][PROTON][CUPTI] User-defined kernel activity records
#10018 opened Apr 13, 2026 by Jokeren Contributor • Draft
[Bugfix] Update truncation from i32 to i8 when storing to i1
#10011 opened Apr 13, 2026 by greatofdream Loading…
4 of 7 tasks
1
7
Add float8_e8m0fnu support to type canonicalization for dot_scaled
#10009 opened Apr 12, 2026 by GeisYaO Loading…
8
Validate incompatible cache_modifier/eviction_policy combinations in NVIDIA backend
#10003 opened Apr 11, 2026 by swjng Contributor Loading…
5 tasks done
5
[DRAFT][DNR] Update FP16 warp-pipelined GEMM
#9978 opened Apr 9, 2026 by jungpark-mlir Contributor • Draft
[TritonGPU] Preserve memdesc_reshape encoding on type propagation
#9973 opened Apr 9, 2026 by Sibylau Loading…
5 of 7 tasks
15
ProTip! no:milestone will show everything without a milestone.