Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

CUDA: add Q2_0 support (#25707)

Browse Source
This commit is contained in:
Pasha Khosravi
2026-07-30 12:33:25 +03:00
committed by GitHub
parent b2f221684f
commit 9b2a088819
20 changed files with 326 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmq.cu
+4
View File
@@ -10,6 +10,9 @@ static void ggml_cuda_mul_mat_q_switch_type(ggml_backend_cuda_context & ctx, con
case GGML_TYPE_Q1_0:
mul_mat_q_case<GGML_TYPE_Q1_0>(ctx, args, stream);
break;
case GGML_TYPE_Q2_0:
mul_mat_q_case<GGML_TYPE_Q2_0>(ctx, args, stream);
break;
case GGML_TYPE_Q4_0:
mul_mat_q_case<GGML_TYPE_Q4_0>(ctx, args, stream);
break;
@@ -262,6 +265,7 @@ bool ggml_cuda_should_use_mmq(enum ggml_type type, int cc, int64_t ne11, int64_t
switch (type) {
case GGML_TYPE_Q1_0:
case GGML_TYPE_Q2_0:
case GGML_TYPE_Q4_0:
case GGML_TYPE_Q4_1:
case GGML_TYPE_Q5_0: