GitLab

* atomic_fix

* atomic_fix

* [BugFix] Add memory order for split version kernel; Remove torch manual seed

* [Lint] Manual

* Remove an incorrect check

* add fp8 pack function

* code lint

* minor fix

* minor fix

* minor fix

* Minor fix

* Minor fix

* add pack function

* code lint

* code lint

* [Benchmark] Update triton and helion baselines in mamba-chuk-scan

* lint

* update mamba baseline version

* update

* update

* [Enhancement] Add missing  primitive after mbarrier init

* lint

Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 5 to 6.
- [Release notes](https://github.com/actions/download-artifact/releases)
- [Commits](https://github.com/actions/download-artifact/compare/v5...v6

)

---
updated-dependencies:
- dependency-name: actions/download-artifact
  dependency-version: '6'
  dependency-type: direct:production
  update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 4 to 5.
- [Release notes](https://github.com/actions/upload-artifact/releases)
- [Commits](https://github.com/actions/upload-artifact/compare/v4...v5

)

---
updated-dependencies:
- dependency-name: actions/upload-artifact
  dependency-version: '5'
  dependency-type: direct:production
  update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* [Feature] Add memory_order PTX for vectorized (2x) atomic add

* [Feature] Add memory_order PTX for all vectorized atomic add

* [Lint]

* test

* [BugFix] FIx init optional argument in alloc_var

* bug fix

* bug fix

* lint fix

* lint fix

---------
Co-authored-by: Lei Wang <34334180+LeiWang1999@users.noreply.github.com>

* fix int32 dtype issue

* lint fix

* lint

* lint fix

---------
Co-authored-by: Zhiwen Mo <zm125@ic.ac.uk>

* [Feature] Support None type as input for T.ptr and T.Tensor

* lint

* lint

* lint

* lint fix

* [Feature] Add vectorized float16 and float32 conversion support in CUDA codegen

* Implemented handling for conversions between float16 and float32 types, specifically for vectorized operations using __half22float2 and __float22half2_rn.
* Enhanced the existing code to support both directions of conversion based on the lane count.
* Improved overall type handling in the VisitExpr_ method for better compatibility with TileLang.

* [Feature] Add float32 to float8 conversion support in CUDA codegen

* Implemented handling for conversion from float32 to float8 (E4M3/E5M2) in the VisitExpr_ method.
* Added vectorized conversion support using __nv_cvt_float2_to_fp8x2 for float2 to fp8x2 transformations.
* Enhanced type handling for better compatibility with TileLang, particularly for float8 types.

* lint

* fix a bug

* [Enhancement] Support lanes=4 cases and add unit test for vectorized cast

* lint

* [Feature] Refactor bf16 convertion operations and remove legacy compile flags

* lint

* [Refactor] Improve scalar handling in CopyNode and update loop partition dtype logic

* Refactored CopyNode::MakeSIMTLoop to handle scalar cases more efficiently by moving the scalar check to the end of the function.
* Updated loop_partition.cc to set a default DataType for thread and vector extents, ensuring compatibility when loop_vars_ is empty.

* lint fix

* remove debug print

* update rules

* ruff check

* other fixes

* fmt

* do not touch examples

* fmt

* [Maint] Remove pre-commit install in `format.sh`

* [Maint] Update uncommitted change detection command

* [Minor] update warning messages

* [Lint] Retire `format.sh` and add `clang-tidy` to GHA workflow

* chore: update clang-tidy settings

* chore: upgrade clang-format and clang-tidy version

* lint: resolve clang-tidy errors

* [Maint] restore format.sh

* [CI] pre-commit autoupdate

* [Minor] fix `command -v` usage

* add alloc_reducer gemv example

* test

* [Lint]

* [BugFix] Freeze the memory order of all atomic_add operations

* [Lint]

* [Atomic] Move on to regional atomic add

* [Lint]

* - carry existing local-var initializer map into OpaqueBlockLower, reattach it to
    generated Allocates and the PrimFunc attrs
  - thread the map through FlattenBuffer and StorageRewrite so flattened/merged
    allocations keep their tl.local_var_init annotations
  - teach annotation handling to accept scalar initializers, resolve buffers, and merge
    with existing stat

* lint fix

* enhance

* lint fix

* lint fix

* • Enable configurable StorageRewrite inplace detection

  - Add kStorageRewriteDetectInplace constant and register the flag with PassContext so C++ code no longer hard-codes the key.
  - Wire StorageRewrite to include TileLang builtin constants and honor the new config toggle when deciding inplace reuse.
  - Document the flag across Python surfaces (PassConfigKey, JIT/autotuner docs) with usage guidance and simplified IR examples.

* lint fix

* add test

* lint fix

* [Cleanup] Remove `tilelang.disable_cache()` calls from example scripts

* lint

* lint

* Improve target docs and helper messaging

  Commit Message:

  - add SUPPORTED_TARGETS metadata and expose describe_supported_targets()
  - relax target validation to accept option suffixes and upgrade error messages
  - document target usage and compute capability mapping in docs/get_started/targets.md
  - note preference for string targets when caching and link the new guide in docs/index.md

* remove american english spelling

* refactor cython wrapper

* optimize

* fix installations

* [BugFix] Add memory order argument for non-vectorized atomic add

* [Lint]

* [BugFix] Memory order

* [Lint]

* [BugFix] Argument in cuda template

* [Lint]

* [Feature] Add GQA backward kernel with varlen input

* [Lint]

* [BugFix] Freeze the memory order of all atomic_add operations

* [Lint]

* [Lint]

* [BugFix] Use release order to boost performance

* [Enhancement] Update async intrinsic handling in inject_fence_proxy

* Added support for wgmma async intrinsics in IsAsyncIntrinsic function.
* Changed handling of unknown externs to treat them as Generic instead of Async, improving accuracy in proxy kind determination.

* test fix

* Update testing/python/transform/test_tilelang_transform_inject_fence_proxy.py
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

---------
Co-authored-by: LeiWang1999 <leiwang1999@outlook.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* Support reduce ss

* lint fix

* test fix

* lint fix

* recommend using T.dynamic instead of T.symbolic

* lint fix

* lint fix

- extend matmul autotune test suite with a symbolic M case and allow run_autotune to accept concrete values for symbolic dims
  - sanitize _kernel_parameters when generating cache keys so symbolic vars serialize deterministically

* [Feature] Support Reduce operators for bitwise and/or/xor

* [Lint]

* Allow dynamic extents in loop partition; warn when layout inversion falls back to NoCheck

* add test and introduce predicate

* test fix

* fix

* enhance

* inverse with level

* test fix

* bug fix