ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-30 19:31:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Minor

Browse Source
This commit is contained in:
Kawrakow
2025-11-18 08:55:36 +00:00
parent 412e4f6e23
commit 0157f78061
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/mmq_id.cu
View File

@@ -472,7 +472,7 @@ void ggml_cuda_mul_mat_q_id(ggml_backend_cuda_context & ctx, const ggml_tensor *
const int64_t s11 = src1->nb[1] / ts_src1; const int64_t s11 = src1->nb[1] / ts_src1;
const int64_t s12 = src1->nb[2] / ts_src1; const int64_t s12 = src1->nb[2] / ts_src1;
const int64_t s13 = src1->nb[2] / ts_src1; const int64_t s13 = src1->nb[3] / ts_src1;
quantize_mmq_q8_1_cuda_id(src1_d, ids_src1, src1_q8_1, src0->type, quantize_mmq_q8_1_cuda_id(src1_d, ids_src1, src1_q8_1, src0->type,
ne10, s11, s12, s13, ne10_padded, ne11_flat, ne12_flat, ne13_flat, stream); ne10, s11, s12, s13, ne10_padded, ne11_flat, ne12_flat, ne13_flat, stream);
CUDA_CHECK(cudaGetLastError()); CUDA_CHECK(cudaGetLastError());