mirror of
https://github.com/huggingface/candle.git
synced 2025-06-21 04:10:46 +00:00
Add the bf16 cuda kernels.
This commit is contained in:
@ -28,6 +28,10 @@ extern "C" __global__ void FN_NAME( \
|
||||
} \
|
||||
} \
|
||||
|
||||
#if __CUDA_ARCH__ >= 800
|
||||
AFFINE_OP(__nv_bfloat16, affine_bf16)
|
||||
#endif
|
||||
|
||||
#if __CUDA_ARCH__ >= 530
|
||||
AFFINE_OP(__half, affine_f16)
|
||||
#endif
|
||||
|
Reference in New Issue
Block a user