Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-04 20:11:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	docs/ops.md
#	docs/ops/SYCL.csv
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	pyproject.toml
#	requirements/requirements-convert_legacy_llama.txt
#	src/CMakeLists.txt
#	src/llama-vocab.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2026-02-07 15:54:02 +08:00
parent 9cf2119cb8 34ba7b5a2f
commit a0a78dacc4
34 changed files with 2371 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+2 -2
View File
@@ -787,9 +787,9 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_POS_EMBD, "weight");
quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_TOKEN_TYPES, "weight");
// do not quantize Mamba's small yet 2D weights
// do not quantize Mamba /Kimi's small conv1d weights
// NOTE: can't use LLM_TN here because the layer number is not known
quantize &= name.find("ssm_conv1d.weight") == std::string::npos;
quantize &= name.find("ssm_conv1d") == std::string::npos;
quantize &= name.find("shortconv.conv.weight") == std::string::npos;
// do not quantize RWKV's small yet 2D weights