Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-02 11:01:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

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
parent fc6e197fdd bbebeec4a8
commit 0f0245161e
103 changed files with 2633 additions and 1170 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model-loader.cpp
+2
View File
@@ -37,6 +37,7 @@ const char * llama_ftype_name(llama_ftype ftype) {
case LLAMA_FTYPE_MOSTLY_F16: name = LLAMA_FTYPE_PREFIX "F16"; break;
case LLAMA_FTYPE_MOSTLY_BF16: name = LLAMA_FTYPE_PREFIX "BF16"; break;
case LLAMA_FTYPE_MOSTLY_Q1_0: name = LLAMA_FTYPE_PREFIX "Q1_0"; break;
case LLAMA_FTYPE_MOSTLY_Q2_0: name = LLAMA_FTYPE_PREFIX "Q2_0"; break;
case LLAMA_FTYPE_MOSTLY_Q4_0: name = LLAMA_FTYPE_PREFIX "Q4_0"; break;
case LLAMA_FTYPE_MOSTLY_Q4_1: name = LLAMA_FTYPE_PREFIX "Q4_1"; break;
case LLAMA_FTYPE_MOSTLY_Q5_0: name = LLAMA_FTYPE_PREFIX "Q5_0"; break;
@@ -768,6 +769,7 @@ llama_model_loader::llama_model_loader(
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;
case GGML_TYPE_Q2_0: ftype = LLAMA_FTYPE_MOSTLY_Q2_0; break;
default:
{
LLAMA_LOG_WARN("%s: unknown type %s\n", __func__, ggml_type_name(type_max));