Ship v0.1.1–v0.1.5: first-live-run fixes and dashboard viewer
- v0.1.1: config persistence — FileHelper paths made absolute (/media/startos/volumes/main/...); relative paths resolved into the JS runtime's ephemeral cwd so action saves never reached /data - v0.1.2: preJobStopContainers (Configure Grading) — docker-stop resident vLLM containers on the head Spark at job start, no auto-restart - v0.1.3: preflight auth (LiteLLM master_key gates /models), poll-until-loaded, crash fast-fail (restarting counts as dead) - v0.1.4: HF_HUB_OFFLINE/TRANSFORMERS_OFFLINE in airgapped serving (--internal network has no DNS); grader _post timeout 600→1800s for ~3.6 tok/s GB10 generation - v0.1.5: dashboard viewer survives the periodic background refresh; download buttons for deck reports, deck JSON, and SCORECARD.md - .gitignore: .startos/ build workspace, start-technologies/ Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Fable 5
parent
1d1074b625
commit
91212322c1
@@ -0,0 +1,13 @@
|
||||
import { VersionInfo } from '@start9labs/start-sdk'
|
||||
|
||||
/** Air-gapped serving fix. ExVer form `<upstream>:<downstream>`. */
|
||||
export const v_0_1_4 = VersionInfo.of({
|
||||
version: '0.1.4:0',
|
||||
releaseNotes:
|
||||
'Air-gapped mode now serves models with HF_HUB_OFFLINE/TRANSFORMERS_OFFLINE ' +
|
||||
'set: the per-job --internal network has no DNS, so without offline mode ' +
|
||||
'the HF hub client crashed on name resolution even with the model fully ' +
|
||||
'cached. Preflight also treats a crash-looping (restarting) vLLM container ' +
|
||||
'as dead and fails fast with its logs instead of waiting out the timeout.',
|
||||
migrations: {},
|
||||
})
|
||||
Reference in New Issue
Block a user