Skip to content

fix Qwen3Embed panic when concurrency #186

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
akshayballal95 merged 1 commit into from
Nov 7, 2025
Merged

fix Qwen3Embed panic when concurrency #186

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
14 changes: 11 additions & 3 deletions rust/src/embeddings/local/qwen3.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,12 +126,20 @@ impl Qwen3Embed for Qwen3Embedder {
for mini_text_batch in text_batch.chunks(batch_size) {
let (token_ids, attention_mask) =
tokenize_batch(&self.tokenizer, mini_text_batch, &self.device)?;

let embeddings: Tensor = {
let mut model = self.model.write().map_err(|e| anyhow::anyhow!("Lock poisoned: {}", e))?;
model.forward(&token_ids, &attention_mask, 0)?.to_dtype(DType::F32)?
let mut model = self
.model
.write()
.map_err(|e| anyhow::anyhow!("Lock poisoned: {}", e))?;
let result = model
.forward(&token_ids, &attention_mask, 0)?
.to_dtype(DType::F32)?;
model.clear_kv_cache();

result
};

self.model.write().map_err(|e| anyhow::anyhow!("Lock poisoned: {}", e))?.clear_kv_cache();
let attention_mask = PooledOutputType::from(attention_mask);
let attention_mask = Some(&attention_mask);
let model_output = ModelOutput::Tensor(embeddings.clone());
Expand Down
Loading