perf: improve streaming generation pipeline

Add CUDA inference hot-path optimizations, safer attention fallback handling, and generation profiling hooks. Improve SSE streaming, browser buffering telemetry, and playback recovery while preserving default audio quality settings.
2026-06-13 03:58:07 +00:00 · 2026-04-30 18:54:14 +01:00
parent a39ec536fd
commit 75b84b211b
9 changed files with 459 additions and 48 deletions
@@ -4,7 +4,7 @@
  "private": true,
  "scripts": {
    "dev": "next dev --turbopack",
-    "build": "next build --turbopack",
+    "build": "next build",
    "start": "next start"
  },
  "dependencies": {