v0.9.0
xorbitsai/inferencev0.9.0Feb 22, 2024by XprobeBot
AI Summary
The v0.9.0 major release introduces Intel GPU support and refactors device-related code. It also adds the Gemma model series and improves the UI to show cluster resources.
Key Highlights
- Refactored device code and added initial Intel GPU support
- Added support for the Gemma series model family
- Updated the web UI to display cluster resource information and replica counts
- Fixed chat completion errors related to message indexing
New Features
- Refactor device related code and add initial Intel GPU support
- Support gemma series model
Full Release Notes
# What's new in 0.9.0 (2024-02-22) These are the changes in inference v0.9.0. ## New features * FEAT: Refactor device related code and add initial Intel GPU support by @notsyncing in https://github.com/xorbitsai/inference/pull/968 * FEAT: Support gemma series model by @aresnow1 in https://github.com/xorbitsai/inference/pull/1024 ## Enhancements * ENH: [UI] Supports `replica` when launching LLM models by @ChengjieLi28 in https://github.com/xorbitsai/inference/pull/1011 * ENH: [UI] Show cluster resource information by @ChengjieLi28 in https://github.com/xorbitsai/inference/pull/1015 ## Bug fixes * BUG: fix chat completion error when indexing body.messages by @fffonion in https://github.com/xorbitsai/inference/pull/1008 * BUG: Fix cache sd 1.5 error by @codingl2k1 in https://github.com/xorbitsai/inference/pull/1013 * BUG: fix typo in modelscope llama-2-13b-chat-GGUF by @qinxuye in https://github.com/xorbitsai/inference/pull/1026 * BUG: Fix missing qwen 1.5 7b gguf by @codingl2k1 in https://github.com/xorbitsai/inference/pull/1027 ## Documentation * DOC: Polish model operation command doc by @onesuper in https://github.com/xorbitsai/inference/pull/1000 * DOC: Fix note on secret_key generation and algorithm selection for OAuth2 by @ChengjieLi28 in https://github.com/xorbitsai/inference/pull/1012 ## New Contributors * @fffonion made their first contribution in https://github.com/xorbitsai/inference/pull/1008 * @notsyncing made their first contribution in https://github.com/xorbitsai/inference/pull/968 **Full Changelog**: https://github.com/xorbitsai/inference/compare/v0.8.5...v0.9.0