CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-15 11:17:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: backwards pass for misc. ops, add tests (#11257)

Browse Source 
* CUDA: backwards pass for misc. ops, add tests

* remove restrict from pointers
This commit is contained in:
Johannes Gäßler
2025-01-16 16:43:38 +01:00
committed by GitHub
parent 681149ced2
commit 9c8dcefe17
18 changed files with 930 additions and 332 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-cuda/unary.cuh
View File

@@ -4,6 +4,7 @@
#define CUDA_STEP_BLOCK_SIZE 256
#define CUDA_GELU_BLOCK_SIZE 256
#define CUDA_SILU_BLOCK_SIZE 256
#define CUDA_SILU_BACK_BLOCK_SIZE 256
#define CUDA_TANH_BLOCK_SIZE 256
#define CUDA_RELU_BLOCK_SIZE 256
#define CUDA_SIGMOID_BLOCK_SIZE 256
@@ -23,6 +24,8 @@ void ggml_cuda_op_gelu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_silu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_silu_back(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_gelu_quick(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_tanh(ggml_backend_cuda_context & ctx, ggml_tensor * dst);