perf: improve streaming generation pipeline

mirror of https://github.com/JezzWTF/vibepod.git synced 2026-06-13 03:58:07 +00:00

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.

This commit is contained in:

LyAhn

2026-04-30 18:54:14 +01:00

parent a39ec536fd

commit 75b84b211b

9 changed files with 459 additions and 48 deletions

server/.python-version

View File

				`@@ -0,0 +1 @@`
				`3.12`