Laurent Mazare c950a5c6b1 Cuda support for the mnist training. (#277) ...

* Cuda support for the mnist training.

* min/max fix + testing.

* Add the argmin/argmax tests.

* More cuda support for argmin/argmax.

* Cuda kernels for argmin and argmax.

2023-07-29 19:48:04 +01:00

..

affine.cu

Add the kernels.

2023-06-30 10:26:56 +01:00

binary_op_macros.cuh

Add some cmp tests. (#233)

2023-07-24 16:53:45 +01:00

binary.cu

Add some cmp tests. (#233)

2023-07-24 16:53:45 +01:00

cast.cu

Bugfix: remove the u8/bf16 conversion kernel as it is ambiguous.

2023-06-30 10:43:32 +01:00

compatibility.cuh

Add the bf16 cuda kernels.

2023-06-29 23:12:02 +01:00

conv.cu

Make it easier to use whisper samples from the repo. (#112)

2023-07-08 18:48:27 +01:00

cuda_utils.cuh

Cuda support for the mnist training. (#277)

2023-07-29 19:48:04 +01:00

fill.cu

Refactor the hierarchy.

2023-06-27 11:57:27 +02:00

indexing.cu

Add a test for scatter add. (#238)

2023-07-25 09:12:14 +01:00

lib.rs

Cuda kernels for IndexAdd/ScatterAdd. (#236)

2023-07-24 21:53:08 +01:00

reduce.cu

Cuda support for the mnist training. (#277)

2023-07-29 19:48:04 +01:00

ternary.cu

Support for where-cond on cuda for u8 and u32. (#274)

2023-07-29 11:48:58 +01:00

unary.cu

Add some flash attn test (#253)

2023-07-26 20:56:00 +01:00