API timeout nostettu 120s → 600s: WASM-inferenssi on hidasta

Kvantisoidun 1.5B-mallin inferenssi on ~0.2 tok/s WASM:ssa.
Pipeline-tehtävät vaativat pidemmän odotusajan.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-06 19:29:15 +03:00
parent f567fd3f8a
commit 1ae1bf98e2

View File

@@ -1080,7 +1080,7 @@ async fn api_chat_completions(
} }
} }
let timeout = tokio::time::timeout(std::time::Duration::from_secs(120), async move { let timeout = tokio::time::timeout(std::time::Duration::from_secs(600), async move {
loop { loop {
let msg_str = match rx.recv().await { let msg_str = match rx.recv().await {
Ok(msg) => msg, Ok(msg) => msg,