morlutoandLeiWang1999 2b4dd80325 [BugFix] Make T.transpose swap only the final two axes (#2757) ...

* [BugFix] Transpose only the final two axes

* [Test] Cover transpose boundary predicate mapping

* [BugFix] Guard transpose bounds with generated indices

---------

Co-authored-by: LeiWang1999 <leiwang1999@outlook.com>

2026-07-24 13:29:24 +08:00

..

amd

[BugFix] Fix MFMA DataType args causing compilation failure on ROCm (#2726)

2026-07-22 16:28:11 +08:00

analysis

[Refactor][Pipeline] Run pipeline rewriting before layout inference and stabilize tiled WS (#2002)

2026-04-07 23:54:55 +08:00

arith

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

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

autotune

[BugFix] Fix segfault when tunable params default to None (#2657)

2026-07-14 14:11:20 +08:00

cache

[CUDA][Cache] Include compile options in binary cache key (#2532)

2026-07-07 00:09:22 +08:00

carver

[BugFix] Fix IntrinInfo repr (#2175)

2026-05-22 16:16:50 +08:00

components

[Feature] Add compiler pass timing profiling (#2622)

2026-07-16 21:36:07 +08:00

contrib

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

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

cpu

[BugFix] Make T.transpose swap only the final two axes (#2757)

2026-07-24 13:29:24 +08:00

cuda

[CUDA] Support fp32x2 ops as reducers (#2637)

2026-07-12 21:47:32 +08:00

debug

[Feature] Add lower-trace support for debugging & rebased (#2725)

2026-07-22 16:27:01 +08:00

fastmath

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

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

issue

[BugFix] Gate TMEM and TMA builtins by CUDA architecture (#2743)

2026-07-23 14:22:05 +08:00

jit

[JIT][TVM-FFI] Reuse executable across kernel launches (#2686)

2026-07-16 17:54:03 +08:00

kernel

[Backend] Support TMA lowering for arbitrary (swizzled) SMEM layout (#2380)

2026-06-18 18:42:01 +08:00

language

[Feature] Support stochastic FP32 to FP16/BF16 casts (#2735)

2026-07-23 11:45:20 +08:00

layout

[CUDA][Pipeline] Fix 1D TMA selection for versioned layouts (#2737)

2026-07-22 21:38:18 +08:00

llvm

[BugFix] Fix llvm auto backend resolution (#2519)

2026-07-06 10:55:13 +08:00

math

[BugFix] Correct IEEE math intrinsic names for fp64/fp16/bf16 (#2619)

2026-07-21 14:04:42 +08:00

metal

[BugFix] Emit Metal barriers for dynamic shared memory (#2738)

2026-07-23 12:39:57 +08:00

profiler

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

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

quantize

[BugFix] Decode FP8 E4M3 special encodings correctly (#2710)

2026-07-20 14:06:46 +08:00

runtime

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

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

target

[Env] Require JSON for default target config (#2491)

2026-06-30 13:27:34 +08:00

tilelibrary

[Backend] Refactor gemm_sp (#2048)

2026-05-19 13:33:41 +08:00

tools

[Feature] Support iket profiler for CUDA backend (#2515)

2026-07-12 20:03:30 +08:00

transform

[BugFix] Preserve loop steps during unswitching (#2741)

2026-07-23 14:41:19 +08:00

utils

[BugFix] Fix sparse int8 default metadata dtype (#2229)

2026-05-21 11:05:10 +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