Starstruk Logo MarkStarstruk

v1.0.0

xorbitsai/inferencev1.0.0Nov 15, 2024by XprobeBot

AI Summary

This is a major version 1.0.0 release featuring the addition of Qwen2.5-Coder variants, basic cancel support for image models, and kvcache support in multi-round chat for MLX.

Key Highlights

  • Added support for Qwen2.5-Coder models (0.5B to 32B).
  • Enhanced MLX capabilities with kvcache for multi-round chat.
  • Introduced basic cancel support for image models.

New Features

  • Basic cancel support for image model
  • Add qwen2.5-coder 0.5B 1.5B 3B 14B 32B
  • support kvcache in multi-round chat for MLX

Full Release Notes

# What's new in 1.0.0 (2024-11-15)
These are the changes in inference v1.0.0.
## New features
* FEAT: Basic cancel support for image model by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2528
* FEAT: Add qwen2.5-coder 0.5B 1.5B 3B 14B 32B by @frostyplanet in https://github.com/xorbitsai/inference/pull/2543
* FEAT: support kvcache in multi-round chat for MLX by @qinxuye in https://github.com/xorbitsai/inference/pull/2534
## Enhancements
* ENH: add normalize to rerank model by @hustyichi in https://github.com/xorbitsai/inference/pull/2509
* ENH: Update fish audio by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2555
## Bug fixes
* BUG: fix variant error for image model by @qinxuye in https://github.com/xorbitsai/inference/pull/2547
## Documentation
* DOC: Add paper citation by @luweizheng in https://github.com/xorbitsai/inference/pull/2533


**Full Changelog**: https://github.com/xorbitsai/inference/compare/v0.16.3...v1.0.0