public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-17 20:03:45 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add Q2_0 quantization: type definition and CPU backend (llama/24448)

Browse Source
This commit is contained in:
Pasha Khosravi
2026-07-10 13:06:42 +03:00
committed by Georgi Gerganov
parent 2061e3b6bf
commit 66e178ec84
11 changed files with 250 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/include/ggml.h
+3 -1
View File
@@ -429,7 +429,8 @@ extern "C" {
GGML_TYPE_MXFP4 = 39, // MXFP4 (1 block)
GGML_TYPE_NVFP4 = 40, // NVFP4 (4 blocks, E4M3 scale)
GGML_TYPE_Q1_0 = 41,
GGML_TYPE_COUNT = 42,
GGML_TYPE_Q2_0 = 42,
GGML_TYPE_COUNT = 43,
};
// precision
@@ -473,6 +474,7 @@ extern "C" {
GGML_FTYPE_MOSTLY_MXFP4 = 25, // except 1d tensors
GGML_FTYPE_MOSTLY_NVFP4 = 26, // except 1d tensors
GGML_FTYPE_MOSTLY_Q1_0 = 27, // except 1d tensors
GGML_FTYPE_MOSTLY_Q2_0 = 28, // except 1d tensors
};
// available tensor operations: