daemondzh 96cf8f979a [OPTIMIZER][BACKEND] Fix an issue in RewriteTensorPtr pass to enable TMA with 8-bit types (#2545) ...

Co-authored-by: Zhicheng Xiong <zhichengx@ipp2-0148.nvidia.com>
Co-authored-by: Zhicheng Xiong <zhichengx@dc7-sim-e12-203.nvidia.com>
Co-authored-by: Zhicheng Xiong <zhichengx@ipp2-1604.nvidia.com>
Co-authored-by: Zhicheng Xiong <zhichengx@ipp2-1608.nvidia.com>
Co-authored-by: goostavz <109190422+goostavz@users.noreply.github.com>

2023-10-31 02:28:27 +00:00

..

NVGPU

Remove wrong dependency between TritonGPU and NVGPU dialect (#2276)

2023-09-11 16:30:13 -07:00

Triton

upgrade llvm to b1115f8c (NFC) (#2403)

2023-10-16 16:38:49 -07:00

TritonGPU

[OPTIMIZER] Remove extra wgmma_wait_group in flash attention (#2399)

2023-10-26 16:35:36 +00:00

TritonNvidiaGPU

[OPTIMIZER][BACKEND] Fix an issue in RewriteTensorPtr pass to enable TMA with 8-bit types (#2545)

2023-10-31 02:28:27 +00:00

CMakeLists.txt

Initial code merge of Hopper support (#2036)

2023-08-07 09:53:04 +08:00