upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-31 15:10:59 -05:00
Code Issues Packages Projects Releases Wiki Activity

ggml : do not break cuBLAS build (Q4_3 is not yet implemented)

Browse Source
This commit is contained in:
Georgi Gerganov
2023-04-20 21:43:50 +03:00
parent 66aab46079
commit 8a1756abdf
1 changed files with 0 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml.c
View File

@@ -8040,9 +8040,6 @@ static void ggml_compute_forward_mul_mat_q_f32(
else if (type == GGML_TYPE_Q4_2) {
dequantize_row_q_cuda = dequantize_row_q4_2_cuda;
}
else if (type == GGML_TYPE_Q4_3) {
dequantize_row_q_cuda = dequantize_row_q4_3_cuda;
}
else {
GGML_ASSERT(false);
}