diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-07-27 07:55:01 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-07-27 07:55:01 +0200 |
| commit | 154e0d75fccf1784fe9ff6fd76a630b66563da3d (patch) | |
| tree | 81ce6dbb5b1900c1aa78a879f0593c694cab9d27 /ggml-cuda/unary.cuh | |
| parent | 0684c3e9c70d49323b4fc517128cbe222cab7f96 (diff) | |
Merge mainline llama.cpp (#3)
* Merging mainline - WIP
* Merging mainline - WIP
AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.
* Merging mainline - fix Metal
* Remove check
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml-cuda/unary.cuh')
| -rw-r--r-- | ggml-cuda/unary.cuh | 33 |
1 files changed, 0 insertions, 33 deletions
diff --git a/ggml-cuda/unary.cuh b/ggml-cuda/unary.cuh deleted file mode 100644 index 4cfb0479..00000000 --- a/ggml-cuda/unary.cuh +++ /dev/null @@ -1,33 +0,0 @@ -#include "common.cuh" - -#define CUDA_GELU_BLOCK_SIZE 256 -#define CUDA_SILU_BLOCK_SIZE 256 -#define CUDA_TANH_BLOCK_SIZE 256 -#define CUDA_RELU_BLOCK_SIZE 256 -#define CUDA_SIGMOID_BLOCK_SIZE 256 -#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); - -void ggml_cuda_op_silu(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); - -void ggml_cuda_op_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst); - -void ggml_cuda_op_sigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst); - -void ggml_cuda_op_hardsigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst); - -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); |