v0.1.0-rc.5
Pre-release
Pre-release
·
168 commits
to main
since this release
Automatically generated release for tag v0.1.0-rc.5.
What's Changed
- [doc] update runtime readme by @brosoul in #318
- Add env for routing strategy override by @varungup90 in #323
- Fix pod autoscaler enqueue issues by @Jeffwan in #329
- Autoscaling benchmark by @kr11 in #337
- Initial lora benchmark result by @Jeffwan in #321
- Adding plotting script by @happyandslow in #338
- Update the downloader performance plot by @Jeffwan in #341
- Reduce pod metrics refresh interval by @varungup90 in #343
- Enable ipv6 for envoy proxy by @varungup90 in #342
- Add benchmark scrips for gateway client side changes by @Jeffwan in #340
- Update the plots based on feedback by @Jeffwan in #346
- [batch] use volcano TOS as batch storage by @xinchen384 in #344
- Add check if no pods are present by @varungup90 in #345
- Add model exists check by @varungup90 in #353
- [Misc] Disable fastapi docs in runtime default action by @brosoul in #350
- Add check for acceptable routing strategies by @varungup90 in #352
- optimize PA messages: const 'HPA' -> actual pa type by @kr11 in #354
- [Misc] Runtime server startup with args by @brosoul in #355
- [Misc] Add python format script by @brosoul in #357
- optimize benchmark scripts for autoscaler, add more logs by @kr11 in #356
- Update the mocked app to cleaner state by @Jeffwan in #361
- Update manifests & docs about service httproute naming trick by @Jeffwan in #362
- Add reference grant to support httprouting for different namespace by @varungup90 in #347
- Validate routing strategy bug fix by @varungup90 in #364
- Bug fix for setting routing strategy via env var by @varungup90 in #369
- Improve the routing env value & flag retrieval by @Jeffwan in #373
- Sync main branch changes to release-0.1 branch by @Jeffwan in #375
- Cut v0.1.0-rc.5 release by @Jeffwan in #376
Full Changelog: v0.1.0-rc.4...v0.1.0-rc.5