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

8
examples/speculative/speculative.cpp
View file

@ -68,7 +68,9 @@ int main(int argc, char ** argv) {
llama_context * ctx_dft = NULL;
// load the target model
std::tie(model_tgt, ctx_tgt) = llama_init_from_gpt_params(params);
llama_init_result llama_init_tgt = llama_init_from_gpt_params(params);
model_tgt = llama_init_tgt.model;
ctx_tgt = llama_init_tgt.context;
// load the draft model
params.model = params.model_draft;
@ -77,7 +79,9 @@ int main(int argc, char ** argv) {
params.n_threads = params.n_threads_draft;
}
params.n_threads_batch = params.n_threads_batch_draft;
std::tie(model_dft, ctx_dft) = llama_init_from_gpt_params(params);
llama_init_result llama_init_dft = llama_init_from_gpt_params(params);
model_dft = llama_init_dft.model;
ctx_dft = llama_init_dft.context;
const bool vocab_type_tgt = llama_vocab_type(model_tgt);
LOG("vocab_type tgt: %d\n", vocab_type_tgt);