vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/llama-server.Dockerfile
#	README.md
#	flake.lock
#	ggml/src/ggml-vulkan.cpp
#	ggml/src/vulkan-shaders/concat.comp
#	ggml/src/vulkan-shaders/pad.comp
#	ggml/src/vulkan-shaders/vulkan-shaders-gen.cpp
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	src/llama.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-08-06 16:33:26 +08:00
commit e1f97f7fb5
55 changed files with 112612 additions and 111077 deletions
Download patch file Download diff file Expand all files Collapse all files

7
examples/server/server.cpp
View file

@ -678,7 +678,10 @@ struct server_context {
// dedicate one sequence to the system prompt
params.n_parallel += 1;
std::tie(model, ctx) = llama_init_from_gpt_params(params);
llama_init_result llama_init = llama_init_from_gpt_params(params);
model = llama_init.model;
ctx = llama_init.context;
params.n_parallel -= 1; // but be sneaky about it
if (model == nullptr) {
LOG_ERROR("unable to load model", {{"model", params.model}});
@ -901,7 +904,7 @@ struct server_context {
slot.params.stream = json_value(data, "stream", false);
slot.params.cache_prompt = json_value(data, "cache_prompt", false);
slot.params.n_predict = json_value(data, "n_predict", default_params.n_predict);
slot.params.n_predict = json_value(data, "n_predict", json_value(data, "max_tokens", default_params.n_predict));
slot.sparams.top_k = json_value(data, "top_k", default_sparams.top_k);
slot.sparams.top_p = json_value(data, "top_p", default_sparams.top_p);
slot.sparams.min_p = json_value(data, "min_p", default_sparams.min_p);