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/full-cuda.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-intel.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.devops/llama-server.Dockerfile
#	.github/workflows/docker.yml
#	docs/docker.md
#	examples/llama-bench/llama-bench.cpp
#	flake.lock
#	ggml/include/ggml.h
#	ggml/src/CMakeLists.txt
#	scripts/sync-ggml.last
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-rope.cpp
This commit is contained in:
Concedo 2024-08-30 10:37:39 +08:00
commit d220495dd4
42 changed files with 100585 additions and 99448 deletions
Download patch file Download diff file Expand all files Collapse all files

7
examples/speculative/speculative.cpp
View file

@ -75,10 +75,11 @@ int main(int argc, char ** argv) {
// load the draft model
params.model = params.model_draft;
params.n_gpu_layers = params.n_gpu_layers_draft;
if (params.n_threads_draft > 0) {
params.n_threads = params.n_threads_draft;
if (params.draft_cpuparams.n_threads > 0) {
params.cpuparams.n_threads = params.draft_cpuparams.n_threads;
}
params.n_threads_batch = params.n_threads_batch_draft;
params.cpuparams_batch.n_threads = params.draft_cpuparams_batch.n_threads;
llama_init_result llama_init_dft = llama_init_from_gpt_params(params);
model_dft = llama_init_dft.model;
ctx_dft = llama_init_dft.context;