vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-22 06:45:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit 'de1aa6fa73' into concedo_experimental

Browse source 
# Conflicts:
#	docs/build.md
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/quants.hpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	tests/test-backend-ops.cpp
#	tests/test-quantize-fns.cpp
This commit is contained in:
Concedo 2026-04-09 17:16:33 +08:00
commit 5529748a01
42 changed files with 799 additions and 2231 deletions
Download patch file Download diff file Expand all files Collapse all files

1
tools/quantize/quantize.cpp
View file

@ -30,6 +30,7 @@ struct quant_option {
};
static const std::vector<quant_option> QUANT_OPTIONS = {
{ "Q1_0", LLAMA_FTYPE_MOSTLY_Q1_0, " 1.125 bpw quantization", },
{ "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", },