Commit Graph
5 Commits
Author SHA1 Message Date
Chaofan Lin 79da657a8f [Analysis] Reject T.Parallel indexing of local buffers (#3041)
[Semantic] Reject T.Parallel indexing of local buffers
2026-08-17 14:31:41 +08:00
penguin_wwy 304291d531 [CPU] Support atomic ops on CPU (#2941) 2026-08-12 15:43:20 +08:00
penguin_wwy c5d0a6c8b7 [CPU] Support reduce ops on CPU (#2893)
* [CPU] Support reduce ops on CPU

* Fix fp16
2026-08-06 17:54:14 +08:00
penguin_wwy af2483f904 [BugFix] Fix llvm auto backend resolution (#2519) 2026-07-06 10:55:13 +08:00
Witherstrike a4ab99e466 [Feature] Add LLVM backend support (#2409)
feat: add end-to-end LLVM backend execution support

Enable LLVM as a TileLang execution backend in CMake and route llvm targets through TVM LLVM codegen during lowering.

Fix tvm_ffi output tensor device inference by deriving the output device from tensor inputs, and add LLVM execution regression tests for matmul, T.gemm, T.copy, and T.While.
2026-06-18 15:25:03 +08:00