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

4
ggml-cuda.cu
View file

@ -2267,6 +2267,9 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
case GGML_OP_SQR:
ggml_cuda_op_sqr(ctx, dst);
break;
case GGML_OP_SQRT:
ggml_cuda_op_sqrt(ctx, dst);
break;
case GGML_OP_CLAMP:
ggml_cuda_op_clamp(ctx, dst);
break;
@ -2830,6 +2833,7 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
case GGML_OP_RMS_NORM:
case GGML_OP_SCALE:
case GGML_OP_SQR:
case GGML_OP_SQRT:
case GGML_OP_CLAMP:
case GGML_OP_CONT:
case GGML_OP_DIAG_MASK_INF: