Skip to content

fix: add QMD_MAX_PARALLEL_CONTEXTS env var to prevent Metal deadlocks #569

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
hteddy64 wants to merge 1 commit into
base: main
Choose a base branch
from
+8 −0
Open

fix: add QMD_MAX_PARALLEL_CONTEXTS env var to prevent Metal deadlocks #569

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
8 changes: 8 additions & 0 deletions src/llm.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -704,6 +704,14 @@ export class LlamaCpp implements LLM {
* half the math cores, with at least 4 threads per context.
*/
private async computeParallelism(perContextMB: number): Promise<number> {
// QMD_MAX_PARALLEL_CONTEXTS: hard cap on context count.
// Set to 1 in MCP mode to prevent node-llama-cpp Metal deadlocks
// when multiple contexts call getEmbeddingFor/rankAll via Promise.all.
const maxOverride = parseInt(process.env.QMD_MAX_PARALLEL_CONTEXTS ?? "", 10);
if (Number.isFinite(maxOverride) && maxOverride > 0) {
return maxOverride;
}

const llama = await this.ensureLlama();

if (llama.gpu) {
Expand Down