diff options
| author | Calvin Laurenson <calvin@laurenson.dev> | 2024-06-16 15:23:04 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-17 00:23:04 +0200 |
| commit | 43b35e38ba371f9a7faa6dca4c5d1e8f698ffd87 (patch) | |
| tree | 11f250899027f3249c9ee15ffaff2048c9b81268 /ggml-cuda/unary.cuh | |
| parent | 19b7a836f6658e18e973af532a5cc6ad6b3a27f8 (diff) | |
Add support for sqrt on CUDA (#7953)
* cuda sqrt support
* enable cuda in pca
* fix comments in pca
* add test
* add sqrt to ggml_backend_cuda_supports_op
* fix test
* new line
* Use F32 sqrtf instead of F64 sqrt
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Diffstat (limited to 'ggml-cuda/unary.cuh')
| -rw-r--r-- | ggml-cuda/unary.cuh | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/ggml-cuda/unary.cuh b/ggml-cuda/unary.cuh index a1d07c04..4cfb0479 100644 --- a/ggml-cuda/unary.cuh +++ b/ggml-cuda/unary.cuh @@ -8,6 +8,7 @@ #define CUDA_HARDSIGMOID_BLOCK_SIZE 256 #define CUDA_HARDSWISH_BLOCK_SIZE 256 #define CUDA_SQR_BLOCK_SIZE 256 +#define CUDA_SQRT_BLOCK_SIZE 256 void ggml_cuda_op_gelu(ggml_backend_cuda_context & ctx, ggml_tensor * dst); @@ -28,3 +29,5 @@ void ggml_cuda_op_hardswish(ggml_backend_cuda_context & ctx, ggml_tensor * dst); void ggml_cuda_op_leaky_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst); void ggml_cuda_op_sqr(ggml_backend_cuda_context & ctx, ggml_tensor * dst); + +void ggml_cuda_op_sqrt(ggml_backend_cuda_context & ctx, ggml_tensor * dst); |