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

RWKV v6: RWKV_WKV op CUDA implementation (#9454)

Browse source 
* ggml: CUDA unary op EXP

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* ggml: rwkv_wkv op CUDA impl

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
This commit is contained in:
Molly Sophia 2024-09-22 10:29:12 +08:00 • committed by GitHub
parent d09770cae7
commit 2a63caaa69
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 168 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -8,6 +8,7 @@
#define CUDA_RELU_BLOCK_SIZE 256
#define CUDA_SIGMOID_BLOCK_SIZE 256
#define CUDA_HARDSIGMOID_BLOCK_SIZE 256
#define CUDA_EXP_BLOCK_SIZE 256
#define CUDA_HARDSWISH_BLOCK_SIZE 256
#define CUDA_SQR_BLOCK_SIZE 256
#define CUDA_SQRT_BLOCK_SIZE 256
@ -32,6 +33,8 @@ 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_exp(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);