Starstruk Logo MarkStarstruk

v1.1.1

xorbitsai/inferencev1.1.1Dec 27, 2024by XprobeBot

AI Summary

This release adds support for F5-TTS-MLX, Qwen2.5-Coder-Instruct, MinicPM-4B on vLLM, QvQ-72B-Preview, and SD3.5 series models. It also includes enhancements for guided decoding and F5-TTS resampling.

Key Highlights

  • Support for F5-TTS-MLX.
  • Support for Qwen2.5-Coder-Instruct for tool calls.
  • Support for MinicPM-4B on vLLM.
  • Support for QvQ-72B-Preview.
  • Support for SD3.5 series model.

New Features

  • support F5-TTS-MLX
  • Support qwen2.5-coder-instruct model for tool calls
  • Support minicpm-4B on vllm
  • support scheduling-policy for vllm
  • Support QvQ-72B-Preview
  • support SD3.5 series model

Full Release Notes

# What's new in 1.1.1 (2024-12-27)
These are the changes in inference v1.1.1.
## New features
* FEAT: support F5-TTS-MLX by @qinxuye in https://github.com/xorbitsai/inference/pull/2671
* FEAT: Support qwen2.5-coder-instruct model for tool calls by @Timmy-web in https://github.com/xorbitsai/inference/pull/2681
* FEAT: Support minicpm-4B on vllm by @Jun-Howie in https://github.com/xorbitsai/inference/pull/2697
* FEAT: support scheduling-policy for vllm by @hwzhuhao in https://github.com/xorbitsai/inference/pull/2700
* FEAT: Support QvQ-72B-Preview by @Jun-Howie in https://github.com/xorbitsai/inference/pull/2712
* FEAT: support SD3.5 series model by @qinxuye in https://github.com/xorbitsai/inference/pull/2706
## Enhancements
* ENH: Guided Decoding OpenAIClient compatibility by @wxiwnd in https://github.com/xorbitsai/inference/pull/2673
* ENH: resample f5-tts-mlx ref audio when sample rate not synching. by @qinxuye in https://github.com/xorbitsai/inference/pull/2678
* ENH: support no images for MLX vlm by @qinxuye in https://github.com/xorbitsai/inference/pull/2670
* ENH: Update fish speech 1.5 by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2672
* ENH: Update cosyvoice 2 by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2684
* REF: Reduce code redundancy by setting default values by @pengjunfeng11 in https://github.com/xorbitsai/inference/pull/2711
## Bug fixes
* BUG: Fix f5tts audio ref by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2680
* BUG: `glm4-chat` cannot apply for continuous batching with transformers backend by @ChengjieLi28 in https://github.com/xorbitsai/inference/pull/2695

## New Contributors
* @Timmy-web made their first contribution in https://github.com/xorbitsai/inference/pull/2681

**Full Changelog**: https://github.com/xorbitsai/inference/compare/v1.1.0...v1.1.1