All pull requests

Pull requests

• feat(stargate,llm-api-gateway): route returning sessions to their last cluster

  #2423·FamousDirector opened Oct 9, 2026Contributor·4 tasks done·

  ·
  1

  6

• feat(llm-routing): simplify shared image and monitoring setup

  #2422·priyaselvaganesan opened Oct 9, 2026Contributor·3 of 4 tasks·

  ·
  3

  

• feat(llm-routing): add an opentelemetry collector dashboard

  #2420·priyaselvaganesan opened Oct 9, 2026Contributor·3 of 4 tasks·

  ·
  1

• feat(llm-routing): prepare k3s GPU clusters with checked scripts

  #2419·kristinapathak opened Oct 9, 2026Collaborator·4 tasks done·

  ·
  1

  

• fix(autoscaler): release distributed locks only for their owner

  #2418·hossiendehghan989 opened Oct 9, 2026·4 tasks done·

  ·
  6

• fix: don't overwrite accountName loop variable for nkey plugin

  #2417·akhil9tiet opened Oct 9, 2026·1 of 4 tasks·

  ·
  1

  9

• ci(release): stop publishing Helm charts from the GitHub tag workflow

  #2415·rohithb-hub opened Oct 9, 2026Contributor·4 tasks done·

  ·
  1

  2

• feat(llm-routing): add Nemotron Nano 12B v2, Nemotron 3.5 Lightning and Qwen3.5-4B Spark recipes

  #2412·jalajthanakinvidia opened Oct 9, 2026Contributor·4 tasks done·

  ·
  1

• fix(nats-auth-callout): report lost NATS connections

  #2410·along-2017 opened Oct 9, 2026Contributor·4 tasks done·

  ·
  1

  1

  

• feat(event-ledger): wire the write cache to the events table

  #2402·adi0106 opened Oct 9, 2026Contributor·3 of 4 tasks·

  ·
  1

• fix(llm-routing): address startup and shared-stack recovery gaps

  #2401·priyaselvaganesan opened Oct 8, 2026Contributor·4 tasks done·

  ·
  1

  

• feat(stack): bump self-managed stack chart pins

  #2393·balajinvda opened Oct 8, 2026Contributor·

  ·
  1

• feat(nvcf-spark-ui): add the demo UI for the LLM routing stack

  #2389·vrv3814 opened Oct 8, 2026Contributor·3 of 4 tasks·

  ·
  1

• fix(nvca): retry initial ICMS registration instead of failing Start fatally

  #2385·apartha-nv opened Oct 8, 2026Contributor·4 tasks done·

  ·
  1

• fix(nvca): run generated init containers as non-root

  #2372·sbaum1994 opened Oct 8, 2026Collaborator·

  ·
  5

• fix(worker-init): declare a non-root image user

  #2371·sbaum1994 opened Oct 8, 2026Collaborator·

  ·
  14

• fix(nvca): reject agent config keys that differ only by case

  #2360·mikeyrcamp opened Oct 7, 2026Contributor·4 tasks done·

  ·
  1

  1

  

• fix(openbao): scope the init-cluster Job Secret RBAC by name

  #2317·sunilthorat09 opened Oct 6, 2026Contributor·

  ·
  1

  3

• fix(nvcf-cli): fail self-hosted check --control-plane and --compute-plane instead of reporting a vacuous pass

  #2311·rohithb-hub opened Oct 6, 2026Contributor·4 tasks done·

  ·
  3

• feat(nvsnap): import gpushare, checkpoint support for GPU memory shared between processes

  #2300·balajinvda opened Oct 6, 2026Contributor·4 tasks done·

  ·
  51

• fix(grpc-proxy): bound concurrent HTTP/2 streams

  #2297·efegokdemir opened Oct 5, 2026·4 tasks done·

  ·
  1

  1

• fix(pylon): exclude cached prompt tokens from fallback TPS

  #2296·efegokdemir opened Oct 5, 2026·4 tasks done·

  ·
  1

  12

• fix(stargate): expire reservations after backend RTT

  #2295·efegokdemir opened Oct 5, 2026·4 tasks done·

  ·
  7

• docs(self-managed): point the 1.0.1 sample-file links at their current path

  #2263·balajinvda opened Oct 5, 2026Contributor·

  ·
  1

  2

• feat(event-ledger): add cache, timing wheel, and metrics

  #2255·adi0106 opened Oct 3, 2026Contributor·2 of 4 tasks·

  ·
  1

  12