Set low VRAM mode

PUT

/api/v1/settings/low-vram

Toggle low VRAM mode. Unloads the current TTS model if one is loaded.

Query Parameters

enabled*Enabled

Enable or disable low VRAM mode

Successful Response

application/json

success*Success

Whether the operation succeeded

changed*Changed

Whether the setting was actually changed

needs_reload*Needs Reload

Whether the TTS model needs to be reloaded

Example Request

curl -X PUT 'http://127.0.0.1:8100/api/v1/settings/low-vram?enabled=true'

Example Request

curl -X PUT 'http://127.0.0.1:8100/api/v1/settings/low-vram?enabled=true'

Example ResponseSchema

{
  "success": true,
  "changed": true,
  "needs_reload": true
}

{  "success": true,  "changed": true,  "needs_reload": true}

Get low VRAM mode GET

Return whether low VRAM mode is enabled.

Get ROCm flash attention GET

Return whether AOTriton flash attention is enabled, and whether it applies here.