mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-15 11:17:31 +00:00
009b709d6e
* CUDA: fused add with rms_norm_mul * Non-broadcast fuse works * Add fused adds * format * Remove n_fuse from template params * Address review comments * Move template inside binbcast
19 lines
838 B
Plaintext
19 lines
838 B
Plaintext
#include "common.cuh"
|
|
|
|
void ggml_cuda_op_norm(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_group_norm(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_rms_norm(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_rms_norm_fused(ggml_backend_cuda_context & ctx, ggml_tensor * dst, ggml_tensor * mul_tensor);
|
|
|
|
void ggml_cuda_op_rms_norm_fused_add(ggml_backend_cuda_context & ctx,
|
|
ggml_tensor * dst,
|
|
ggml_tensor * mul_tensor,
|
|
ggml_tensor * add_tensor);
|
|
|
|
void ggml_cuda_op_rms_norm_back(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_l2_norm(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|