Lei Wang 88747fcdda [Language] Support tile operator T.cumsum (#423) ...

* [Feature] Implement CumSum operation in TileLang

* Added CumSumOp class for cumulative sum operations, including argument validation and lowering logic.
* Introduced CumSum2D template for CUDA, supporting both forward and reverse cumulative sums.
* Created tests for CumSum functionality in shared memory and fragment contexts.
* Updated language interface to include cumsum operation, enhancing the reduction capabilities of TileLang.
* Refactored reduce.py to support cumsum functionality with appropriate memory allocation and copying mechanisms.

* lint fix

2025-04-22 22:04:54 +08:00

..

amd

Add preliminary support for bf16 for AMD (#388)

2025-04-16 11:48:58 -05:00

autotune

[AutoTune] Refactor AutoTuneArtifact to utilize kernel as context instead of profiler (#344)

2025-04-07 13:36:35 +08:00

cache

[Refactor] Deprecated T.Buffer as arguments and rename related calls into T.Tensor (#281)

2025-03-26 13:42:52 +08:00

carver

[Refactor] Phaseout LLVM Dependency by Making it Optional (#247)

2025-03-20 20:08:20 +08:00

cpu

[Refactor] Deprecated T.Buffer as arguments and rename related calls into T.Tensor (#281)

2025-03-26 13:42:52 +08:00

debug

[Refactor] Deprecated T.Buffer as arguments and rename related calls into T.Tensor (#281)

2025-03-26 13:42:52 +08:00

dynamic

[BugFix] Address should aligned with access size in tail split (#401)

2025-04-17 00:29:38 +08:00

ir

[Refactor] Phaseout LLVM Dependency by Making it Optional (#247)

2025-03-20 20:08:20 +08:00

issue

[Refactor] Deprecated T.Buffer as arguments and rename related calls into T.Tensor (#281)

2025-03-26 13:42:52 +08:00

jit

[Refactor] Deprecated T.Buffer as arguments and rename related calls into T.Tensor (#281)

2025-03-26 13:42:52 +08:00

kernel

[Enhancement][Pipeline] More precise copy code block detection in pipeline (#384)

2025-04-12 23:13:21 +08:00

language

[Language] Support tile operator T.cumsum (#423)

2025-04-22 22:04:54 +08:00

pass_config

[Enhancement] Support pass config disable_warp_specialize to disable auto specialization on hopper (#357)

2025-04-08 17:41:32 +08:00

primitives

[AutoTune] Refactor AutoTuneArtifact to utilize kernel as context instead of profiler (#344)

2025-04-07 13:36:35 +08:00

tilelibrary

[Refactor] Deprecated T.Buffer as arguments and rename related calls into T.Tensor (#281)

2025-03-26 13:42:52 +08:00

transform

[Enhancement] Support pass config disable_warp_specialize to disable auto specialization on hopper (#357)

2025-04-08 17:41:32 +08:00

webgpu

[Refactor] Deprecated T.Buffer as arguments and rename related calls into T.Tensor (#281)

2025-03-26 13:42:52 +08:00