Janis Eccarius 587ea19e0e fix(spark-analytics): increase NIM timeout and trim max_tokens to avoid read timeouts ...

70B model at 30-50 tok/s was exceeding the 30s urllib timeout for larger
outputs. Raise server timeout to 60s, add browser AbortController at 65s
so the UI fails gracefully. Trim max_tokens (row: 300, dataset: 512) to
keep generation well inside the window.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-06-21 17:58:29 +02:00

..

cronjobs.yaml

fix: co-locate analytics driver pods with spark-worker for RWO PVC access

2026-06-21 16:06:51 +02:00

kustomization.yaml

feat(spark-analytics): add 7 CronJobs, results webview, and LiChess staging demo

2026-06-21 15:09:49 +02:00

pvc.yaml

feat(nci): add Spark analytics Kubernetes manifests

2026-06-15 22:25:28 +02:00

rbac.yaml

feat(nci): add Spark analytics Kubernetes manifests

2026-06-15 22:25:28 +02:00

serviceaccount.yaml

feat(nci): add Spark analytics Kubernetes manifests

2026-06-15 22:25:28 +02:00

streaming.yaml

fix(spark): use file:/// so driver serves analytics.jar to executors over HTTP

2026-06-17 01:33:13 +02:00

webview.yaml

fix(spark-analytics): increase NIM timeout and trim max_tokens to avoid read timeouts

2026-06-21 17:58:29 +02:00