ignaciosicaandGitHub bae20e5043 Generic PTX wmma rendering [pr] (#8632) ...

* make wmma rendering dtype size generic

* use var instead of calculating multiple times

* compact rendering

2025-01-15 09:31:48 -08:00

..

__init__.py

free intermediate buffers in the jit [pr] (#8581)

2025-01-12 15:41:41 -08:00

cstyle.py

CUDA Turing TC (#8597)

2025-01-14 10:35:14 -08:00

llvmir.py

move llvm_bf16_cast to the renderer [pr] (#8502)

2025-01-05 13:02:41 +02:00

ptx.py

Generic PTX wmma rendering [pr] (#8632)

2025-01-15 09:31:48 -08:00

wgsl.py

more typing work [pr] (#8345)

2024-12-19 21:46:35 -08:00