vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-11 21:32:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/docker.yml
#	ggml/src/ggml-opencl/kernels/mul_mm_f16_f32_l4_lm.cl
#	ggml/src/ggml-opencl/kernels/mul_mm_f32_f32_l4_lm.cl
#	ggml/src/ggml-sycl/rope.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/rope.tmpl.wgsl
#	requirements/requirements-convert_legacy_llama.txt
#	tests/test-backend-ops.cpp
#	tests/test-rope.cpp
#	tools/server/README.md
This commit is contained in:
Concedo 2025-10-31 10:52:57 +08:00
commit 2b00e55356
35 changed files with 1905 additions and 290 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-quant.cpp
View file

@ -656,7 +656,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
gguf_set_val_f32(ctx_out.get(), o.key, o.val_f64);
} else if (o.tag == LLAMA_KV_OVERRIDE_TYPE_INT) {
// Setting type to UINT32. See https://github.com/ggml-org/llama.cpp/pull/14182 for context
gguf_set_val_u32(ctx_out.get(), o.key, (uint32_t)abs(o.val_i64));
gguf_set_val_u32(ctx_out.get(), o.key, (uint32_t)std::abs(o.val_i64));
} else if (o.tag == LLAMA_KV_OVERRIDE_TYPE_BOOL) {
gguf_set_val_bool(ctx_out.get(), o.key, o.val_bool);
} else if (o.tag == LLAMA_KV_OVERRIDE_TYPE_STR) {