Daniel Hiltgen 15e3611d3d logs: quiet down context canceled on completion and scheduler noise (#12553) ...

* logs: quiet down context canceled on completion

If the client closes the connection before Completion finishes, we were
logging at error level implying the runner crashed which was misleading.

time=2025-10-08T22:59:20.566-07:00 level=ERROR source=server.go:1490 msg="post predict" error="Post \"http://127.0.0.1:57736/completion\": context canceled"

* quiet down scheduler log error on expected case

Since we don't hold the lock while performing memory load calculations, other
runners can unload in parallel, so finding no runner to unload is a valid scenario
which we shouldn't log at error level.

2025-10-09 10:37:47 -07:00

..

llm_darwin.go

…

llm_linux.go

…

llm_windows.go

…

memory_test.go

Use runners for GPU discovery (#12090)

2025-10-01 15:12:32 -07:00

memory.go

discover: Disable flash attention for Jetson Xavier (CC 7.2)

2025-10-08 09:56:15 -07:00

server_test.go

Use runners for GPU discovery (#12090)

2025-10-01 15:12:32 -07:00

server.go

logs: quiet down context canceled on completion and scheduler noise (#12553)

2025-10-09 10:37:47 -07:00

status.go

…