vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-19 16:31:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

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
src/llama-quant.cpp
View file

@ -801,6 +801,7 @@ ggml_type llama_ftype_get_default_type(llama_ftype ftype) {
case LLAMA_FTYPE_MOSTLY_F16: return GGML_TYPE_F16;
case LLAMA_FTYPE_MOSTLY_BF16: return GGML_TYPE_BF16;
case LLAMA_FTYPE_ALL_F32: return GGML_TYPE_F32;
case LLAMA_FTYPE_MOSTLY_Q1_0: return GGML_TYPE_Q1_0;
case LLAMA_FTYPE_MOSTLY_MXFP4_MOE: return GGML_TYPE_MXFP4;