Commit Graph
6 Commits
Author SHA1 Message Date
steveandClaude Opus 5 0358fe321e internal/router: priority queues so batch jobs yield to interactive requests
The GPU is a size-1 resource, so a single long job monopolises the box for its
whole duration and every interactive request queues behind it. Callers can now
declare intent with an X-LlamaSwap-Priority header and the serial scheduler
dispatches by score instead of by arrival.

- X-LlamaSwap-Priority: signed integer, 0 default, absent/unparseable means 0.
  interactive/normal/batch aliases resolve to +100/0/-100. Values are not
  clamped: the caller composes band and any per-user offset itself.
- serial dispatch score = priority + swap affinity + aging. Bands sit 100 apart
  so a small caller offset orders work inside a band without crossing one;
  aging is unbounded so low-priority work cannot starve.
- routing.scheduler.settings.serial.{agingDivisor,swapAffinityBonus}, defaulting
  to 60s/point and +10. swapAffinityBonus is capped at 99 so it can never
  promote a request into the next band.
- fifo adds the header to its per-model priority, so the header is not silently
  ignored under that scheduler.
- /metrics exports per-band queue depth, oldest wait and dispatch counts, plus
  counters for how often aging or swap affinity changed the pick. Each request
  records its priority, band, score and queue wait in the activity log.

Note swapAffinityBonus defaults to 10, so equal-priority requests for the
already-loaded model now run before older requests that need a swap. Set it to
0 for the previous strict arrival order.

fixes #9

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01WUyhZBgv8BBCC5MduX88gE
2026-08-07 02:12:08 -04:00
steveandClaude Opus 4.8 542b79dacf internal/router/scheduler: add serial scheduler, default on this fork
Validate JSON Schema / validate-schema (push) Successful in 9m53s
Linux CI / run-tests (push) Failing after 15m57s
Windows CI / run-tests (push) Has been cancelled
Add a strict one-model-at-a-time scheduler. Requests run in exact
arrival order; at most one runs at a time; switching to a different
model evicts every other running model first so a single model occupies
memory at a time. Unlike fifo it never reorders or batches same-model
requests, and it ignores group/matrix co-residency entirely, making the
single-model guarantee a property of the scheduler rather than the config.

- new Serial scheduler implementing the Scheduler interface
- register "serial" in scheduler.New; default routing.scheduler.use to
  "serial" at config load (fifo still selectable for upstream behavior)
- update config schema, example config, and config defaults tests

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-06-28 12:17:32 -04:00
Benson Wong 6cf1317341 schedule,shared: move concurrency 429 limits into scheduler code (#849)
- make concurrency limiting the scheduler.Scheduler's responsibility
- eliminate the separate concurrency limit middleware 
- move concurrencyLimit logic into scheduler.FIFO to maintain backwards compatibility
- add HTTPError from #834 

Updates #834
2026-06-15 22:35:12 -07:00
Benson Wong ed77385d08 ui: improve manual model load and cancel (#847)
- When a model is manually loaded show a cancel buttton and a queued
status
- Implement cancellation in scheduler.Scheduler interface and FIFO
scheduler
- Add cache bust query parameter to bypass browser cache

Fixes #844
2026-06-14 13:38:10 -07:00
Benson Wong 62aea0e83d internal/router,server,shared: refactor auth, libs (#839)
- refactor shared http functionality into internal/shared/http.go
- remove stripping of Authorization and x-api-key
- add Request Context middleware to internal/server
- add /ui and /metrics behind auth middleware, fixes #717

Fix #717
Updates: #834
2026-06-13 10:19:04 -07:00
Benson Wong 9b3a33d7b9 Implement new scheduler (#823)
- introduce internal/router/scheduler to decouple routing, swapping and
queuing into interface contracts.
- introduce a new `routing` configuration section that supersedes
`matrix` and `group` while maintaining backwards compatibility
- add FIFO scheduler with prioritized queuing 
- add internal/router/design.md as developer documentation on
implementing new schedulers and routers

Fixes #797
2026-06-10 20:34:25 -07:00