vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add support for sqrt on CUDA (#7953)

Browse source 
* 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>
This commit is contained in:
Calvin Laurenson 2024-06-16 15:23:04 -07:00 • committed by GitHub
parent 19b7a836f6
commit 43b35e38ba
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 71 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml-cuda/unary.cuh
View file

@ -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);