Skip to content

build(deps): bump llama-cpp-2 from 0.1.132 to 0.1.133 #123

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

Merged
codito merged 2 commits into from
Feb 12, 2026
Merged

build(deps): bump llama-cpp-2 from 0.1.132 to 0.1.133 #123

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2bc1f1e
build(deps): bump llama-cpp-2 from 0.1.132 to 0.1.133
dependabot[bot] Feb 9, 2026
ab38298
fix: replace deprecated methods
codito Feb 12, 2026
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
33 changes: 17 additions & 16 deletions Cargo.lock
View file
Open in desktop

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

2 changes: 1 addition & 1 deletion crates/core/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ tracing-subscriber.workspace = true
notify.workspace = true
minijinja = { version = "2.15.1", features = ["builtins", "json"] }
minijinja-contrib = { version = "2.15.1", features = ["pycompat"] }
llama-cpp-2 = "=0.1.132"
llama-cpp-2 = "=0.1.133"

[dev-dependencies]
tempfile = { workspace = true, features = [] }
Expand Down
16 changes: 11 additions & 5 deletions crates/core/src/provider/gguf/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,12 +8,11 @@ use anyhow::{Context, Result, anyhow};
use async_trait::async_trait;
use futures::stream::BoxStream;
use llama_cpp_2::token::LlamaToken;
use llama_cpp_2::{LogOptions, send_logs_to_tracing};
use llama_cpp_2::{LogOptions, TokenToStringError, send_logs_to_tracing};
use llama_cpp_2::{
context::params::LlamaContextParams,
llama_backend::LlamaBackend,
llama_batch::LlamaBatch,
model::Special,
model::{AddBos, LlamaModel, params::LlamaModelParams},
sampling::LlamaSampler,
};
Expand Down Expand Up @@ -293,9 +292,16 @@ impl CompletionModel for GgufBaseModel {
}

// Get token bytes and decode
let token_bytes = model
.token_to_bytes(token, Special::Tokenize)
.map_err(|e| anyhow!("Token conversion failed: {e}"))?;
let token_bytes = match model.token_to_piece_bytes(token, 8, true, None) {
Err(TokenToStringError::InsufficientBufferSpace(required)) => {
let required = (-required)
.try_into()
.expect("Error buffer size is positive");
model.token_to_piece_bytes(token, required, true, None)
}
res => res,
}
.map_err(|e| anyhow!("Token conversion failed: {e}"))?;

let mut last_chunk = String::with_capacity(32);
let _ = decoder.decode_to_string(&token_bytes, &mut last_chunk, false);
Expand Down