GitLab

* - 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

Bumps [actions/checkout](https://github.com/actions/checkout) from 4 to 5.
- [Release notes](https://github.com/actions/checkout/releases)
- [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md)
- [Commits](https://github.com/actions/checkout/compare/v4...v5

)

---
updated-dependencies:
- dependency-name: actions/checkout
  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>

[Enhancement] Deprecate split&sum in attn bwd examples on Hopper and migrate to vectorized atomic add (#1065)

* [Refactor][Example] Update linear attention examples and add tests

- Refactored the backward and forward linear attention kernels to use shared memory and atomic additions for improved performance.
- Introduced L2 normalization in the main functions of both examples.
- Added a new test suite for the linear attention examples to ensure correctness and performance.
- Updated argument parsing in the main functions for better usability.

* upd docstring for tma atomic add

* lint

* Add flash-linear-attention dependency to requirements.txt

* Rename main function to chunk_linear_attn_bwd

* Rename main function to chunk_linear_attn_fwd

* chore

---------
Co-authored-by: LeiWang1999 <leiwang1999@outlook.com>
Co-authored-by: Lei Wang <34334180+LeiWang1999@users.noreply.github.com>

* Add document PYTHONPATH build path

* update fp8 benchmark result

* remove redpath

* remove path

* tflops fix

* [CI]:Reduce test shapes to avoid OOM errors during CI.

* rabbit

* Increase number of processes for pytest from 2 to 4

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

* [Refactor] Refactor Pass  to support recursive load/store rewrite

* lint

* recursive collect conds for call_extern

* fix name

* [Lint]: [pre-commit.ci] auto fixes [...]

* lint

* [Lint]: [pre-commit.ci] auto fixes [...]

* lint

* [Lint]: [pre-commit.ci] auto fixes [...]

* address comment

* rename pad_value to safe_value

* lint

* add oob store test

* [Lint]: [pre-commit.ci] auto fixes [...]

* fix

* fix

---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* [Enhancement] Improve layout inference for local buffer handling in parallel operations

* Added logic to check if a loop only manipulates "local" buffers, which affects thread binding decisions.
* Updated the condition for determining parallel loop execution to account for local buffer stores.
* Cleaned up comments for clarity and future considerations.

* [Refactor] Clean up parallel loop condition formatting in layout inference

* Reformatted the condition for determining parallel loop execution for better readability.
* Maintained existing logic while enhancing code clarity for future modifications.

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

* improve CUDA compiler detection in CMake

* Minor fix

* remove last dimension stride must be 1 constraint

* add vectorize test

* minor fix

* [Lint]: [pre-commit.ci] auto fixes [...]

---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

[Enhancement] Add support for symbolic dimensions in Cython kernel adapter and improve static shape validation in wrapper (#1024)

* [Enhancement] Add support for symbolic dimensions in Cython kernel adapter and improve static shape validation in wrapper

* [BugFix] Fix shape mismatch and deprecate `T.if()` in fused_moe example

* [Fix] Add `is_symbolic_expr` function to check for symbolic expressions in TIR

- Introduced a new utility function `is_symbolic_expr` to determine if an expression is a symbolic expression, enhancing type checking capabilities.
- Updated shape handling in `CythonKernelAdapter` to utilize the new function, improving handling for symbolic shapes.

* [CI] fix ROCm CI

* feat: add a hook to error out on no test runs

[Bugfix] Improves compatibility when checking for MPS availability in different PyTorch builds. (#1051)

* update

* format

* rabbit

* [BugFix] Phaseout dependency of Triton in sink examples to make CI happy

- Added `benchmark_gqa_sink_fwd.py` and `benchmark_mha_sink_fwd.py` to evaluate performance of GQA and MHA attention mechanisms using Triton.
- Refactored existing attention sink implementations to remove Triton kernel definitions from the reference programs, streamlining the code.
- Updated input generation and benchmarking logic to enhance configurability and performance measurement.
- Improved overall structure and organization of the examples for better clarity and usability.

* [Lint]: [pre-commit.ci] auto fixes [...]

---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* refactor: merge test CI workflow files into one

* chore: set `UV_INDEX_STRATEGY=unsafe-best-match`

* feat: add AST test with Python 3.8

* feat: implement manual caching mechanism for self-hosted runners

* refactor: simplify cache logic for self-hosted runners

* chore: clear uv cache on failure

* chore: print format.sh output to logs

* chore: improve uv caching

* chore: disable parallel test

* chore: use `PYTHONDEVMODE=1` in CI

* feat: enable coredump generation

* fix: fix perfbench condition

* Revert "feat: enable coredump generation"

This reverts commit c52da65cb572932e09905d08c43a39ec3cf47c54.

* chore: move example CI down

* Revert "chore: move example CI down"

This reverts commit 9d8e65055e01d955c5268a9a6705d270c2de0d57.

* chore: skip example `test_example_mha_sink_bwd_bhsd`

* chore: skip example `test_example_gqa_sink_bwd_bhsd`

* fix: fix example argument passing

* fix: loosen test criteria

* chore: rename `CMAKE_CONFIG...