vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-04-28 03:30:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge commit 'fbd441c379' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	AGENTS.md
#	ci/run.sh
#	docs/build.md
#	embd_res/templates/LFM2.5-Instruct.jinja
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cuda/fattn.cu
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/htp-msg.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-div.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	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/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	scripts/hip/gcn-cdna-vgpr-check.py
#	scripts/sync-ggml.last
#	tests/test-chat.cpp
This commit is contained in:
Concedo 2026-04-03 01:06:02 +08:00
commit 5dee1a1cbb
37 changed files with 982 additions and 372 deletions
Download patch file Download diff file Expand all files Collapse all files

39
include/llama.h
View file

@ -383,22 +383,33 @@ extern "C" {
size_t n_samplers;
};
struct llama_model_tensor_override {
const char * pattern;
enum ggml_type type;
};
struct llama_model_imatrix_data {
const char * name;
const float * data;
size_t size;
};
// model quantization parameters
typedef struct llama_model_quantize_params {
int32_t nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
enum llama_ftype ftype; // quantize to this llama_ftype
enum ggml_type output_tensor_type; // output tensor type
enum ggml_type token_embedding_type; // token embeddings tensor type
bool allow_requantize; // allow quantizing non-f32/f16 tensors
bool quantize_output_tensor; // quantize output.weight
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
bool pure; // quantize all tensors to the default type
bool keep_split; // quantize to the same number of shards
bool dry_run; // calculate and show the final quantization size without performing quantization
void * imatrix; // pointer to importance matrix data
void * kv_overrides; // pointer to vector containing overrides
void * tensor_types; // pointer to vector containing tensor types
void * prune_layers; // pointer to vector containing layer indices to prune
int32_t nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
enum llama_ftype ftype; // quantize to this llama_ftype
enum ggml_type output_tensor_type; // output tensor type
enum ggml_type token_embedding_type; // token embeddings tensor type
bool allow_requantize; // allow quantizing non-f32/f16 tensors
bool quantize_output_tensor; // quantize output.weight
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
bool pure; // quantize all tensors to the default type
bool keep_split; // quantize to the same number of shards
bool dry_run; // calculate and show the final quantization size without performing quantization
const struct llama_model_imatrix_data * imatrix; // pointer to importance matrix data
const struct llama_model_kv_override * kv_overrides; // pointer to kv overrides
const struct llama_model_tensor_override * tt_overrides; // pointer to tensor overrides
const int32_t * prune_layers; // pointer to layer indices to prune
} llama_model_quantize_params;
typedef struct llama_logit_bias {