ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 07:04:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Prevent assert with quantized K cache and no FA

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-08-08 11:18:26 +03:00
parent 58f3bda0ae
commit 0dce7f9128
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.cu
View File

@@ -1647,7 +1647,7 @@ static void ggml_cuda_op_mul_mat(
}
const int64_t src1_col_stride = split && used_devices > 1 ? MUL_MAT_SRC1_COL_STRIDE : ne11;
if (!(split && used_devices > 1) && quantization_done && ne11 == 1 && ne12 > 1 && ne13 == 1) {
if (!(split && used_devices > 1) && quantization_done && ne11 == 1 && ne12 > 1 && ne13 == 1 && ne02 == ne12 && ne02 == dst->ne[2]) {
//printf("invoking fast path for %s x %s\n", src0->name, src1->name);
int id = ctx.device;
char * src0_dd_i = dev[id].src0_dd;