kubeai 0.13.0
What's Changed
- helm: update chart versions and appVersion by @samos123 in #344
- Cache optimized routing ("PrefixHash" load balancing - i.e. CHWBL) by @nstogner in #333
- Benchmark prefix hashing on 8 replicas using H100 and Llama 3.1 70B by @samos123 in #360
- update vllm GPU image to v0.6.6.post1 by @samos123 in #363
- feat(charts/kubeai): Add NodePort and LoadBalancer support with optional port value for kubeai and openwebui services by @MRColorR in #362
New Contributors
Full Changelog: v0.12.0...v0.13.0