Jonathan KirkwoodandClaude Fable 5
506e6c79bd
- Secondary-Spark models now work in air-gapped mode: the LiteLLM proxy is dual-homed onto the default bridge (docker network connect) to reach the secondary's published vLLM port; grader containers stay on the --internal network with zero egress. The head-only enforcement is replaced by a secondary-configured check. - Extraction runs in parallel with grading when the extractor's model and every grader model in the wave sit on different Sparks (separate GPUs). - Keep-warm: single-wave jobs no longer tear the wave down between decks (was a ~6-min 31B reload per deck); a kept-warm wave that fails preflight is restarted once. Adjudicator reuses the live wave when its model is already serving instead of cycling the shared proxy. - clear_resident_containers (preJobStopContainers) now stops names on every configured Spark; health() reports containers on both Sparks. - Verified with a mocked dry-run of the full job loop (3 decks: one bring-up, zero mid-job teardowns, parallel overlap, stale-wave restart). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
17 lines
593 B
TypeScript
17 lines
593 B
TypeScript
import { VersionGraph } from '@start9labs/start-sdk'
|
|
import { v_0_1_0 } from './v_0_1_0'
|
|
import { v_0_1_1 } from './v_0_1_1'
|
|
import { v_0_1_2 } from './v_0_1_2'
|
|
import { v_0_1_3 } from './v_0_1_3'
|
|
import { v_0_1_4 } from './v_0_1_4'
|
|
import { v_0_1_5 } from './v_0_1_5'
|
|
import { v_0_1_6 } from './v_0_1_6'
|
|
import { v_0_1_7 } from './v_0_1_7'
|
|
import { v_0_1_8 } from './v_0_1_8'
|
|
|
|
/** The current version MUST be the first argument (`current`). */
|
|
export const versions = VersionGraph.of({
|
|
current: v_0_1_8,
|
|
other: [v_0_1_7, v_0_1_6, v_0_1_5, v_0_1_4, v_0_1_3, v_0_1_2, v_0_1_1, v_0_1_0],
|
|
})
|