kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-10 13:10:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Pasha Khosravi
2026-07-07 12:05:47 -07:00
committed by GitHub
parent c198af4dc2
commit bec4772f6a
17 changed files with 262 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/quantize/quantize.cpp
+1
View File
@@ -33,6 +33,7 @@ struct quant_option {
static const std::vector<quant_option> QUANT_OPTIONS = {
{ "Q1_0", LLAMA_FTYPE_MOSTLY_Q1_0, " 1.125 bpw quantization", },
{ "Q2_0", LLAMA_FTYPE_MOSTLY_Q2_0, " 2.25 bpw quantization (group 64)", },
{ "Q4_0", LLAMA_FTYPE_MOSTLY_Q4_0, " 4.34G, +0.4685 ppl @ Llama-3-8B", },
{ "Q4_1", LLAMA_FTYPE_MOSTLY_Q4_1, " 4.78G, +0.4511 ppl @ Llama-3-8B", },
{ "MXFP4_MOE",LLAMA_FTYPE_MOSTLY_MXFP4_MOE," MXFP4 MoE", },