vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-04 13:39:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	tests/test-backend-ops.cpp
#	tests/test-quantize-fns.cpp
#	tools/server/README.md
#	tools/ui/src/lib/constants/settings-registry.ts
This commit is contained in:
Concedo 2026-07-11 09:20:40 +08:00
commit 0f0245161e
103 changed files with 2633 additions and 1170 deletions
Download patch file Download diff file Expand all files Collapse all files

1
tools/quantize/quantize.cpp
View file

@ -32,6 +32,7 @@ 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", },