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

cuda : refactor into multiple files (#6269)

Browse source
This commit is contained in:
slaren 2024-03-25 13:50:23 +01:00 • committed by GitHub
parent ad3a0505e3
commit ae1f211ce2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
59 changed files with 9154 additions and 8987 deletions
Download patch file Download diff file Expand all files Collapse all files

7
ggml-cuda/mmvq.cuh Normal file
View file

@ -0,0 +1,7 @@
#include "common.cuh"
void ggml_cuda_op_mul_mat_vec_q(
ggml_backend_cuda_context & ctx,
const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const char * src0_dd_i, const float * src1_ddf_i,
const char * src1_ddq_i, float * dst_dd_i, const int64_t row_low, const int64_t row_high, const int64_t src1_ncols,
const int64_t src1_padded_row_size, cudaStream_t stream);