ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 15:14:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

delete unused and noncompiling mmvq functions

Browse Source
This commit is contained in:
Andrew Keen Chan
2025-05-20 16:55:45 +00:00
parent 46712586b3
commit 60a948bf44
2 changed files with 0 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
ggml/src/ggml-cuda/iqk_mmvq.cu
View File

@@ -590,11 +590,6 @@ __device__ __forceinline__ float vec_dot_iq2_ks_q8_1(
+ __low2float(bq8_1[4*(i4/4)+3].ds) * sumi4);
}
__device__ __forceinline__ float vec_dot_iq2_kt_q8_1(
const void * __restrict__ vbq, const block_q8_1 * __restrict__ bq8_1, const int & kbx, const int & iqs) {
return 0.f;
}
#define VDR_IQ3_K_Q8_1_MMVQ 4
#define VDR_IQ3_K_Q8_1_MMQ 4
@@ -829,13 +824,6 @@ void mul_mat_vec_iq2_ks_q8_1_cuda(
iqk_mul_mat_vec_q_cuda<GGML_TYPE_IQ2_KS, VDR_IQ2_KS_Q8_1_MMVQ, vec_dot_iq2_ks_q8_1>(vx, vy, dst, ids_data, ncols_x, nrows_x, nrows_y, ncols_y, nrows_dst, ne2, nb02, nb12, nb2, ids_nb0, stream);
}
void mul_mat_vec_iq2_kt_q8_1_cuda(
const void * vx, const void * vy, float * dst,
const int ncols_x, const int nrows_x, const int nrows_y, const int ncols_y, const int nrows_dst, cudaStream_t stream) {
iqk_mul_mat_vec_q_cuda<GGML_TYPE_IQ2_KT, VDR_IQ2_KS_Q8_1_MMVQ, vec_dot_iq2_kt_q8_1>(vx, vy, dst, ncols_x, nrows_x, nrows_y, ncols_y, nrows_dst, stream);
}
void mul_mat_vec_iq5_k_q8_1_cuda(
const void * vx, const void * vy, float * dst, const char * ids_data,
const int ncols_x, const int nrows_x, const int nrows_y, const int ncols_y, const int nrows_dst,

4
ggml/src/ggml-cuda/iqk_mmvq.cuh
View File

@@ -51,10 +51,6 @@ void mul_mat_vec_iq2_ks_q8_1_cuda(
const int ncols_x, const int nrows_x, const int nrows_y, const int ncols_y, const int nrows_dst,
const int ne2, const uint64_t nb02, const uint64_t nb12, const uint64_t nb2, const int64_t ids_nb0, cudaStream_t stream);
void mul_mat_vec_iq2_kt_q8_1_cuda(
const void * vx, const void * vy, float * dst,
const int ncols_x, const int nrows_x, const int nrows_y, const int ncols_y, const int nrows_dst, cudaStream_t stream);
void mul_mat_vec_iq1_bn_q8_1_cuda(
const void * vx, const void * vy, float * dst, const char * ids_data,
const int ncols_x, const int nrows_x, const int nrows_y, const int ncols_y, const int nrows_dst,