Commit Graph

4 Commits

Author SHA1 Message Date
Ettore Di Giacinto
3387bfaee0 feat(api): add support for open responses specification (#8063)
* feat: openresponses

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add ttl settings, fix tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: register cors middleware by default

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* satisfy schema

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Logitbias and logprobs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add grammar

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* SSE compliance

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* tool JSON conversion

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* support background mode

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* swagger

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* drop code. This is handled in the handler

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Small refactorings

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* background mode for MCP

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-01-17 22:11:47 +01:00
Richard Palethorpe
99b5c5f156 feat(api): Allow tracing of requests and responses (#7609)
* feat(api): Allow tracing of requests and responses

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* feat(traces): Add traces UI

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
2025-12-29 11:06:06 +01:00
Ettore Di Giacinto
c844b7ac58 feat: disable force eviction (#7725)
* feat: allow to set forcing backends eviction while requests are in flight

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat: try to make the request sit and retry if eviction couldn't be done

Otherwise calls that in order to pass would need to shutdown other
backends would just fail.

In this way instead we make the request sit and retry eviction until it
succeeds. The thresholds can be configured by the user.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* add tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* expose settings to CLI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Update docs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-12-25 14:26:18 +01:00
Ettore Di Giacinto
50f9c9a058 feat(watchdog): add Memory resource reclaimer (#7583)
* feat(watchdog): add GPU reclaimer

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Handle vram calculation for unified memory devices

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Support RAM eviction, set watchdog interval from runtime settings

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-12-16 09:15:18 +01:00