Releases: helixml/helix
1.4.4 - New Image Generation Codebase and Capabilities
This release contains a new image generation codebase that allows Helix much more flexibility over what image generation models are added.
To celebrate this release we've baked a selection of the latest image generation models from Stability.AI and black-forest-labs into the -large
runner images only.
In the future we will tinker with the baked model selection to reduce the size of the base images and add the code to allow fine-tuning.
What's Changed
- Small clean up of empty chars and unusued vars. by @milosgajdos in #614
- Remove llamaindex by @milosgajdos in #615
- chore(deps): bump github.com/hashicorp/go-retryablehttp from 0.7.4 to 0.7.7 in /operator by @dependabot in #616
- chore(deps): bump github.com/hashicorp/go-retryablehttp from 0.7.4 to 0.7.7 by @dependabot in #617
- chore: small cleanup by @milosgajdos in #618
- Update actionable system prompt by @milosgajdos in #619
- feat(runner): add basic diffusers server by @philwinder in #613
New Contributors
- @milosgajdos made their first contribution in #614
- @dependabot made their first contribution in #616
Full Changelog: 1.4.3...1.4.4
1.4.4 RC1 Diffusers Testing
1.4.4-rc1 chore(ci): bump runner base-images
1.4.3 - Image inference quick fix
What's Changed
- fix(ci): fix gh release parsing in .drone.yml by @philwinder in #598
- fix(api): quick fix to sdxl image inference by @philwinder in #600
This quickly fixes a regression in image inference due to a breaking change in an old library. More finesse will come later. Image fine-tuning doesn't work.
Full Changelog: 1.4.2...1.4.3
1.4.2 - Bugfix
What's Changed
- fix(api): pass custom query parameters to tool by @philwinder in #597
Full Changelog: 1.4.1...1.4.2
1.4.1 - finetuning upgrades, scheduler dashboard
What's Changed
- feat(axolotl): upgrade axolotl and use llama3.2-1B as the model by @philwinder in #590
- fix(axolotl): fix axolotl crash when no LOG_LEVEL set by @philwinder in #591
- fix(runner): update base image tag in drone build script by @philwinder in #592
- fix(ui): reinstate fine-tuning progress in UI by @philwinder in #593
- feat(ui): add desired state to dashboard by @philwinder in #595
- chore(ui): fix dashboard with more runners by @philwinder in #596
Full Changelog: 1.4.0...1.4.1
1.4.1-rc4
What's Changed
- fix(ui): reinstate fine-tuning progress in UI by @philwinder in #593
Full Changelog: 1.4.1-rc3...1.4.1-rc4
1.4.1-rc3
What's Changed
- fix(runner): update base image tag in drone build script by @philwinder in #592
Full Changelog: 1.4.1-rc2...1.4.1-rc3
1.4.1-rc2
What's Changed
- fix(axolotl): fix axolotl crash when no LOG_LEVEL set by @philwinder in #591
Full Changelog: 1.4.1-rc1...1.4.1-rc2
1.4.1-rc1
What's Changed
- feat(axolotl): upgrade axolotl and use llama3.2-1B as the model by @philwinder in #590
Full Changelog: 1.4.0...1.4.1-rc1
1.4.0 - CI/CD for fully private cloud native GenAI
What's Changed
- test(openai-api): fixes test after new scheduler by @philwinder in #585
- Feature/operator, roundtripping by @lukemarsden in #586
- Fix/v1alpha1 by @lukemarsden in #587
- fix: tell helm the correct url for a localhost port-forward by @lukemarsden in #589
Full Changelog: 1.3.7...1.4.0