Lei Wang f91a8c9b07 [Layout][Reducer] Preserve vectorized reducer update plans (#3100) ...

[Layout] Preserve vectorized reducer update plans

Treat reducer_update as a transparent expression during layout vector-shape analysis. This lets contribution loads determine the planned width instead of forcing update nests onto scalar-shaped layouts before reducer materialization.\n\nAdd a CUDA regression that checks the shared-to-fragment copy remains packed and verifies the reducer result.

2026-08-27 22:20:13 +08:00

..

amd

[BugFix][ROCm] Reject sub-wavefront block sizes instead of crashing (#2918)

2026-08-08 09:38:51 -07:00

analysis

[Analysis] Reject T.Parallel indexing of local buffers (#3041)

2026-08-17 14:31:41 +08:00

arith

[Bugfix] Fix non-divisible nested modulo simplification (#3065)

2026-08-25 19:25:52 +08:00

autotune

[Refactor] Remove obsolete compiler and runtime paths (#3086)

2026-08-26 02:11:38 +08:00

backend

[Backend] Add unified backend resolution policy (#2318)

2026-08-06 02:41:57 +08:00

cache

[Runtime][Cache] Detect and repair corrupted cache entries (#3074)

2026-08-24 17:15:45 +08:00

carver

[BugFix][Carver] Parse lettered SM arch strings in check_sm_version (#2891)

2026-08-07 15:18:16 +08:00

components

[Cleanup] Remove obsolete disable-fast-math pass config (#3098)

2026-08-27 19:37:40 +08:00

contrib

[BugFix] Isolate cross-compiler options per invocation (#2728)

2026-07-22 19:00:59 +08:00

cpu

[Analysis] Reject T.Parallel indexing of local buffers (#3041)

2026-08-17 14:31:41 +08:00

cuda

[CUDA][Reduce] Add per-reduce control for FP32x2 accumulation (#3057)

2026-08-21 13:18:06 +08:00

debug

[Debug][TIR][JIT] Unify pass instrumentation per compilation (#2923)

2026-08-10 15:37:25 +08:00

fastmath

[BugFix] Fix failed ties-away-from-zero round compile on bfloat16/float8 (#2873)

2026-08-10 16:44:34 +08:00

issue

[Bugfix][CUDA] Fix UB in packed 8-bit vector stores (#3092)

2026-08-27 19:47:41 +08:00

jit

[Runtime][Cache] Remove separate cache temporary directory (#3069)

2026-08-23 21:33:47 +08:00

kernel

[Testing] Gate CUDA-only tests so non-CUDA backends can run the suite (#2863)

2026-08-04 18:22:40 +08:00

language

[CUDA] Add 16-bit overloads for CUTLASS fast-math functions (#3097)

2026-08-27 17:17:24 +08:00

layout

[Layout] Reject non-round-tripping inferred inverses (#3090)

2026-08-27 18:04:12 +08:00

llvm

[Analysis] Reject T.Parallel indexing of local buffers (#3041)

2026-08-17 14:31:41 +08:00

math

[BugFix][CUDA] Provide htan overloads for fp16/bf16 tangent (#2894)

2026-08-11 15:22:06 +08:00

metal

[BugFix][Metal] Preserve pointer address spaces for byte offsets (#2925)

2026-08-14 16:54:58 +08:00

profiler

[tilelang] Fix CUPTI cache flush filtering (#2244)

2026-05-22 16:15:53 +08:00

quantize

[CUDA] Add SM120 NVF4 block-scale MMA support (#2364)

2026-07-30 18:10:10 +08:00

runtime

[TIR][IR] Update to use tirx (#2216)

2026-05-20 15:38:13 +08:00

target

[Backend] Add unified backend resolution policy (#2318)

2026-08-06 02:41:57 +08:00

tilelibrary

[Refactor] Move example-only helpers out of tilelang package (#2761)

2026-07-24 18:03:34 +08:00

tools

[Tool] Add official compile-only CLI (#3045)

2026-08-25 14:11:20 +08:00

transform

[Layout][Reducer] Preserve vectorized reducer update plans (#3100)

2026-08-27 22:20:13 +08:00

utils

[Refactor] Move example-only helpers out of tilelang package (#2761)

2026-07-24 18:03:34 +08:00

webgpu

[Enhancement] Update examples and tests for improved type handling functionality (#1448)

2025-12-17 14:41:25 +08:00

test_version_provider.py

[Build] Fix sdist version metadata (#2374)

2026-06-11 20:40:16 +08:00