GitLab

add phi2 mem

* dont clamp ctx size in `PredictServerFit`

* minimum 4 context

* remove context warning

Bump VRAM buffer back up

Under stress scenarios we're seeing OOMs so this should help stabilize
the allocations under heavy concurrency stress.

fix typo

only forward some env vars

log clean up

Fix race in shutdown logic

Ensure the runners are terminated

Wait for GPU free memory reporting to converge

The GPU drivers take a while to update their free memory reporting, so we need
to wait until the values converge with what we're expecting before proceeding
to start another runner in order to get an accurate picture.

Record more GPU information

This cleans up the logging for GPU discovery a bit, and can
serve as a foundation to report GPU information in a future UX.

Harden subprocess reaping

routes: skip invalid filepaths

Doc container usage and workaround for nvidia errors

Updated sample code as per warning notification from the package maintainers

Add GPU usage

Detect noexec and report a better error

This records more GPU usage information for eventual UX inclusion.

* Add preflight OPTIONS handling and update CORS config

- Implement early return with HTTP 204 (No Content) for OPTIONS requests in allowedHostsMiddleware to optimize preflight handling.

- Extend CORS configuration to explicitly allow 'Authorization' headers and 'OPTIONS' method when OLLAMA_ORIGINS environment variable is set.

* allow auth, content-type, and user-agent headers

* Update routes.go

routes: fix show llava models