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/common.cuh
+7
View File
@@ -977,6 +977,13 @@ struct ggml_cuda_type_traits<GGML_TYPE_Q1_0> {
static constexpr int qi = QI1_0;
};
template<>
struct ggml_cuda_type_traits<GGML_TYPE_Q2_0> {
static constexpr int qk = QK2_0;
static constexpr int qr = QR2_0;
static constexpr int qi = QI2_0;
};
template<>
struct ggml_cuda_type_traits<GGML_TYPE_Q4_0> {
static constexpr int qk = QK4_0;