Skip to content

feat: Replace once_cell with std::sync::OnceLock, and improve error handling in the backend initialization. #9

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: Replace once_cell with std::sync::OnceLock, and improve error handling in the backend initialization. #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 1 addition & 2 deletions reference_apps/llamacpp_bindings/Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 0 additions & 1 deletion reference_apps/llamacpp_bindings/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@ llama-cpp-2 = { git = "https://github.com/utilityai/llama-cpp-rs", rev = "77af62
hf-hub = { version = "0.3.2" }
anyhow = "1.0.91"
encoding_rs = "0.8.34"
once_cell = "1.20.2"

[features]
cuda = ["llama-cpp-2/cuda"]
Expand Down
18 changes: 11 additions & 7 deletions reference_apps/llamacpp_bindings/src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
use anyhow::{ Context, Result};
use anyhow::{anyhow, Context, Result};
use llama_cpp_2::llama_backend::LlamaBackend;
use llama_cpp_2::model::{LlamaModel, params::LlamaModelParams, Special, AddBos};
use llama_cpp_2::token::data_array::LlamaTokenDataArray;
Expand All @@ -7,12 +7,11 @@ use llama_cpp_2::llama_batch::LlamaBatch;
use std::num::NonZeroU32;
use std::path::PathBuf;
use encoding_rs::UTF_8;
use hf_hub::api::sync::ApiBuilder;
use llama_cpp_2::ggml_time_us;
use std::time::Duration;
use once_cell::sync::OnceCell;
use std::sync::OnceLock;

static BACKEND: OnceCell<LlamaBackend> = OnceCell::new();
static BACKEND: OnceLock<Result<LlamaBackend>> = OnceLock::new();

// Enum for selecting model type
#[derive(Debug, Clone)]
Expand Down Expand Up @@ -102,10 +101,11 @@ impl LLM {
/// Loads the model based on the provided ModelType
pub fn load(model_type: ModelType, load_params: LoadParams) -> Result<Self> {
// Initialize backend only once
let backend = BACKEND.get_or_try_init(LlamaBackend::init)?;
let backend = BACKEND.get_or_init(|| LlamaBackend::init().map_err(anyhow::Error::from));
let backend = backend.as_ref().map_err(|e| anyhow!(e.to_string()))?;

let model_path = match model_type {
ModelType::Local { path } => path
ModelType::Local { path } => path,
};

let model_params = LlamaModelParams::from(load_params);
Expand All @@ -122,7 +122,11 @@ impl LLM {
where
F: FnMut(&str),
{
let backend = BACKEND.get().expect("Backend not initialized");
let backend = BACKEND
.get()
.expect("Backend not initialized")
.as_ref()
.map_err(|e| anyhow!(e.to_string()))?;
let t_main_start = ggml_time_us();
let max_tokens = inference_params.max_tokens;
let ctx_params = LlamaContextParams::from(inference_params);
Expand Down