Starstruk Logo MarkStarstruk

v0.14.3

xorbitsai/inferencev0.14.3Aug 25, 2024by XprobeBot

AI Summary

Introduces ChatTTS voice support, SD3-medium inpainting, Fish Speech model, and CogVLM2-video. Adds UI parameters for models and LMDeploy support for InternVL2 video capabilities.

Key Highlights

  • ChatTTS speech voice support
  • SD3-medium inpainting support
  • Fish Speech model support
  • CogVLM2-video support

New Features

  • ChatTTS speech voice support
  • SD3-medium inpainting support
  • Fish Speech model support
  • CogVLM2-video support
  • InternVL2 video support via LMDeploy

Full Release Notes

# What's new in 0.14.3 (2024-08-25)
These are the changes in inference v0.14.3.
## New features
* FEAT: ChatTTS speech voice support encoded speaker str by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2096
* FEAT: [UI] Add other parameters to other models besides the LLM model. by @yiboyasss in https://github.com/xorbitsai/inference/pull/2129
* FEAT: support SD3-medium inpainting by @qinxuye in https://github.com/xorbitsai/inference/pull/2137
* feat: 🎸 Added the model dtype parameter for embedding (currently only supported for models gte-Qwen2). by @Zzzz1111 in https://github.com/xorbitsai/inference/pull/2120
* FEAT: Support fish speech model by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2119
* FEAT: support CogVLM2-video by @Minamiyama in https://github.com/xorbitsai/inference/pull/2110
* FEAT: Support LMDeploy for internvl2 and fix finish reasion miss at internvl stream by @amumu96 in https://github.com/xorbitsai/inference/pull/2145
## Enhancements
* ENH: make internvl2 support video by @Minamiyama in https://github.com/xorbitsai/inference/pull/2104
* ENH: support process_image with padding for image_to_image by @qinxuye in https://github.com/xorbitsai/inference/pull/2109
* REF: use utils._decode_image replacing same codes in individual vl files by @Minamiyama in https://github.com/xorbitsai/inference/pull/2105
## Bug fixes
* BUG: fix asyncio.Queue error in benchmark by @Dawnfz-Lenfeng in https://github.com/xorbitsai/inference/pull/2113
* BUG: fix deleting cache by @qinxuye in https://github.com/xorbitsai/inference/pull/2114
* Bug: fix audio ability errorwhen get instance info by @amumu96 in https://github.com/xorbitsai/inference/pull/2147
* BUG: fix docker conflict by @amumu96 in https://github.com/xorbitsai/inference/pull/2156
## Documentation
* DOC: add more doc about ChatTTS by @qinxuye in https://github.com/xorbitsai/inference/pull/2108
* DOC: remove models deleted by @qinxuye in https://github.com/xorbitsai/inference/pull/2122
* DOC: Add doc for fish speech and cogvlm2 video by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2149
## Others
* [Bug]: Fix concurrent ops in worker initialization  by @frostyplanet in https://github.com/xorbitsai/inference/pull/2125

## New Contributors
* @Zzzz1111 made their first contribution in https://github.com/xorbitsai/inference/pull/2120

**Full Changelog**: https://github.com/xorbitsai/inference/compare/v0.14.2...v0.14.3