vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-07 17:22:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	ggml/CMakeLists.txt
#	ggml/cmake/ggml-config.cmake.in
#	ggml/src/CMakeLists.txt
#	models/templates/README.md
#	tools/imatrix/imatrix.cpp
This commit is contained in:
Concedo 2025-08-05 19:24:29 +08:00
commit 7590a0ea39
22 changed files with 1122 additions and 421 deletions
Download patch file Download diff file Expand all files Collapse all files

36
common/arg.cpp
View file

@ -26,6 +26,7 @@
#include <cstdarg>
#include <filesystem>
#include <fstream>
#include <list>
#include <regex>
#include <set>
#include <string>
@ -2377,20 +2378,35 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
throw std::invalid_argument("unknown buffer type");
}
// FIXME: this leaks memory
params.tensor_buft_overrides.push_back({strdup(tensor_name.c_str()), buft_list.at(buffer_type)});
// keep strings alive and avoid leaking memory by storing them in a static vector
static std::list<std::string> buft_overrides;
buft_overrides.push_back(tensor_name);
params.tensor_buft_overrides.push_back({buft_overrides.back().c_str(), buft_list.at(buffer_type)});
}
}
));
add_opt(common_arg(
{"--cpu-moe"},
"use CPU for Mixture of Experts (MoE) weights",
{"--cpu-moe", "-cmoe"},
"keep all Mixture of Experts (MoE) weights in the CPU",
[](common_params & params) {
params.tensor_buft_overrides.push_back({"\\.ffn_up_exps\\.weight$", ggml_backend_cpu_buffer_type()});
params.tensor_buft_overrides.push_back({"\\.ffn_down_exps\\.weight$", ggml_backend_cpu_buffer_type()});
params.tensor_buft_overrides.push_back({"\\.ffn_gate_exps\\.weight$", ggml_backend_cpu_buffer_type()});
params.tensor_buft_overrides.push_back({"\\.ffn_(up|down|gate)_exps", ggml_backend_cpu_buffer_type()});
}
).set_env("LLAMA_ARG_CPU_MOE"));
add_opt(common_arg(
{"--n-cpu-moe", "-ncmoe"}, "N",
"keep the Mixture of Experts (MoE) weights of the first N layers in the CPU",
[](common_params & params, int value) {
if (value < 0) {
throw std::invalid_argument("invalid value");
}
for (int i = 0; i < value; ++i) {
// keep strings alive and avoid leaking memory by storing them in a static vector
static std::list<std::string> buft_overrides;
buft_overrides.push_back(string_format("blk\\.%d\\.ffn_(up|down|gate)_exps", i));
params.tensor_buft_overrides.push_back({buft_overrides.back().c_str(), ggml_backend_cpu_buffer_type()});
}
}
).set_env("LLAMA_ARG_N_CPU_MOE"));
add_opt(common_arg(
{"-ngl", "--gpu-layers", "--n-gpu-layers"}, "N",
"number of layers to store in VRAM",
@ -2651,10 +2667,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
add_opt(common_arg(
{"--output-format"}, "{gguf,dat}",
string_format("output format for imatrix file (default: %s)", params.imat_dat ? "dat" : "gguf"),
string_format("output format for imatrix file (default: %s)", params.imat_dat > 0 ? "dat" : "gguf"),
[](common_params & params, const std::string & value) {
/**/ if (value == "gguf") { params.imat_dat = false; }
else if (value == "dat") { params.imat_dat = true; }
/**/ if (value == "gguf") { params.imat_dat = -1; }
else if (value == "dat") { params.imat_dat = 1; }
else { throw std::invalid_argument("invalid output format"); }
}
).set_examples({LLAMA_EXAMPLE_IMATRIX}));

2
common/common.h
View file

@ -435,7 +435,7 @@ struct common_params {
int32_t n_out_freq = 10; // output the imatrix every n_out_freq iterations
int32_t n_save_freq = 0; // save the imatrix every n_save_freq iterations
int32_t i_chunk = 0; // start processing from this chunk
bool imat_dat = false; // whether the legacy imatrix.dat format should be output
int8_t imat_dat = 0; // whether the legacy imatrix.dat format should be output (gguf <= 0 < dat)
bool process_output = false; // collect data for the output tensor
bool compute_ppl = true; // whether to compute perplexity