vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	Makefile
#	README.md
#	common/CMakeLists.txt
#	common/common.cpp
#	common/common.h
#	examples/embedding/embedding.cpp
#	examples/imatrix/imatrix.cpp
#	examples/infill/infill.cpp
#	examples/parallel/parallel.cpp
#	examples/perplexity/perplexity.cpp
#	examples/rpc/README.md
#	examples/save-load-state/save-load-state.cpp
#	examples/server/README.md
#	examples/speculative/speculative.cpp
#	tests/test-sampling.cpp
This commit is contained in:
Concedo 2024-09-10 16:39:23 +08:00
commit a947558e0e
45 changed files with 2628 additions and 6743 deletions
Download patch file Download diff file Expand all files Collapse all files

7
examples/server/server.cpp
View file

@ -1,6 +1,8 @@
#include "utils.hpp"
#include "arg.h"
#include "common.h"
#include "sampling.h"
#include "json-schema-to-grammar.h"
#include "llama.h"
#include "build-info.h"
@ -614,7 +616,7 @@ struct server_context {
gpt_params params;
llama_batch batch;
llama_batch batch = {};
bool clean_kv_cache = true;
bool add_bos_token = true;
@ -2424,8 +2426,7 @@ int main(int argc, char ** argv) {
// own arguments required by this example
gpt_params params;
auto options = gpt_params_parser_init(params, LLAMA_EXAMPLE_SERVER);
if (!gpt_params_parse(argc, argv, params, options)) {
if (!gpt_params_parse(argc, argv, params, LLAMA_EXAMPLE_SERVER)) {
return 1;
}