Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: add LLAMA_CPP_N_THREADS env #742

Merged
merged 4 commits into from
Nov 9, 2023
Merged

feat: add LLAMA_CPP_N_THREADS env #742

Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d137bf4
feat: add LLAMA_CPP_N_THREADS and LLAMA_CPP_N_THREADS_BATCH envs
erfanium Nov 9, 2023
0831a3c
apply format
erfanium Nov 9, 2023
b01ccec
improve: use LLAMA_CPP_N_THREADS for both n_threads and n_threads_batch
erfanium Nov 9, 2023
ae0c701
Update crates/llama-cpp-bindings/src/engine.cc
wsxiaoys Nov 9, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion crates/llama-cpp-bindings/src/engine.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -316,8 +316,13 @@ std::unique_ptr<TextInferenceEngine> create_engine(bool use_gpu, rust::Str model
llama_context_params ctx_params = llama_context_default_params();
ctx_params.n_ctx = N_CTX * parallelism;
ctx_params.n_batch = N_BATCH;
if (const char* n_threads = std::getenv("LLAMA_CPP_N_THREADS")) {
ctx_params.n_threads = std::stoi(n_threads);
erfanium marked this conversation as resolved.
Show resolved Hide resolved
}
if (const char* n_threads_batch = std::getenv("LLAMA_CPP_N_THREADS_BATCH")) {
ctx_params.n_threads_batch = std::stoi(n_threads_batch);
}
llama_context* ctx = llama_new_context_with_model(model, ctx_params);

return std::make_unique<TextInferenceEngineImpl>(
owned<llama_model>(model, llama_free_model),
owned<llama_context>(ctx, llama_free),
Expand Down