steve cecb89880e feat(server): dispatch /v1/videos and /v1/videos/sync by model ...

Registers the OpenAI/vLLM-Omni video generation endpoints as
model-dispatched routes so llama-swap can swap in video upstreams
(e.g. vllm serve <model> --omni, or a ComfyUI shim exposing the same
shape). Extraction is content-type driven, so both multipart form and
JSON bodies resolve the model field.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AXQxVhXBw8PwFAtsVrXSmj

2026-07-12 09:25:55 -04:00

..

cache

Introduce new routing backend (#790)

2026-05-28 21:47:01 -07:00

chain

Introduce new routing backend (#790)

2026-05-28 21:47:01 -07:00

config

internal/router/scheduler: add serial scheduler, default on this fork

2026-06-28 12:17:32 -04:00

event

Introduce new routing backend (#790)

2026-05-28 21:47:01 -07:00

logmon

Introduce new routing backend (#790)

2026-05-28 21:47:01 -07:00

perf

perf: add vendor-agnostic GPU monitoring for Windows (experimental) (#779)

2026-06-16 21:49:09 -07:00

process

internal/process,server: fix unload regression (#828)

2026-06-09 20:49:58 -07:00

ring

proxy,ui: add performance monitoring with Prometheus metrics (#743)

2026-05-09 13:29:22 -07:00

router

internal/router/scheduler: add serial scheduler, default on this fork

2026-06-28 12:17:32 -04:00

server

feat(server): dispatch /v1/videos and /v1/videos/sync by model

2026-07-12 09:25:55 -04:00

shared

proxy: meter /upstream requests via metrics middleware (#858)

2026-06-17 17:38:52 -07:00

watcher

internal/config,watcher: add -config-dir (#873)

2026-06-24 20:48:51 -07:00