Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-17 08:19:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'de1aa6fa73e135839109e09fec1a0997f4207b2a' 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
parent f371bb14d4 de1aa6fa73
commit 5529748a01
42 changed files with 799 additions and 2231 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model-loader.cpp
+2
View File
@@ -36,6 +36,7 @@ static std::string llama_model_ftype_name(llama_ftype ftype) {
case LLAMA_FTYPE_ALL_F32: return "all F32";
case LLAMA_FTYPE_MOSTLY_F16: return "F16";
case LLAMA_FTYPE_MOSTLY_BF16: return "BF16";
case LLAMA_FTYPE_MOSTLY_Q1_0: return "Q1_0";
case LLAMA_FTYPE_MOSTLY_Q4_0: return "Q4_0";
case LLAMA_FTYPE_MOSTLY_Q4_1: return "Q4_1";
case LLAMA_FTYPE_MOSTLY_Q5_0: return "Q5_0";
@@ -759,6 +760,7 @@ llama_model_loader::llama_model_loader(
case GGML_TYPE_IQ4_XS: ftype = LLAMA_FTYPE_MOSTLY_IQ4_XS; break;
case GGML_TYPE_IQ3_S: ftype = LLAMA_FTYPE_MOSTLY_IQ3_S; break;
case GGML_TYPE_NVFP4: ftype = LLAMA_FTYPE_MOSTLY_NVFP4; break;
case GGML_TYPE_Q1_0: ftype = LLAMA_FTYPE_MOSTLY_Q1_0; break;
default:
{
LLAMA_LOG_WARN("%s: unknown type %s\n", __func__, ggml_type_name(type_max));