v0.4.2
版本发布时间: 2023-09-15 19:26:03
xorbitsai/inference最新发布版本:v0.16.2(2024-11-01 18:09:08)
What's new in 0.4.2 (2023-09-15)
These are the changes in inference v0.4.2.
New features
- FEAT: concurrent generation by @codingl2k1 in https://github.com/xorbitsai/inference/pull/417
- FEAT: Support gguf by @aresnow1 in https://github.com/xorbitsai/inference/pull/446
- FEAT: Support OpenBuddy by @codingl2k1 in https://github.com/xorbitsai/inference/pull/444
Enhancements
- ENH: client support desc model by @UranusSeven in https://github.com/xorbitsai/inference/pull/442
- ENH: caching from self-hosted storage by @UranusSeven in https://github.com/xorbitsai/inference/pull/419
- ENH: Assign worker sub pool at runtime instead of pre-allocated by @ChengjieLi28 in https://github.com/xorbitsai/inference/pull/437
- ENH: add benchmark script by @UranusSeven in https://github.com/xorbitsai/inference/pull/451
Bug fixes
- BUG: Fix restful client for embedding models by @aresnow1 in https://github.com/xorbitsai/inference/pull/439
- BUG: cmdline double line breaker by @UranusSeven in https://github.com/xorbitsai/inference/pull/441
- BUG: no error raised on unsupported fmt by @UranusSeven in https://github.com/xorbitsai/inference/pull/443
- BUG: Xinferecen list failed if embedding models are launched by @aresnow1 in https://github.com/xorbitsai/inference/pull/452
Tests
- TST: skip self-hosted storage tests by @UranusSeven in https://github.com/xorbitsai/inference/pull/453
Documentation
- DOC: fix baichuan-2 and make naming consistent by @UranusSeven in https://github.com/xorbitsai/inference/pull/432
- DOC: update hot topics by @UranusSeven in https://github.com/xorbitsai/inference/pull/456
Others
- CI: Fix Windows CI by @codingl2k1 in https://github.com/xorbitsai/inference/pull/440
New Contributors
- @ChengjieLi28 made their first contribution in https://github.com/xorbitsai/inference/pull/437
Full Changelog: https://github.com/xorbitsai/inference/compare/v0.4.1...v0.4.2