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/ggml-cuda.cu
+2
View File
@@ -4802,6 +4802,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_TYPE_F32:
case GGML_TYPE_F16:
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:
@@ -4840,6 +4841,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_TYPE_BF16:
case GGML_TYPE_I32:
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: