Starstruk Logo MarkStarstruk

v0.15.1

xorbitsai/inferencev0.15.1Sep 14, 2024by XprobeBot

AI Summary

This release introduces extensive new features including SD API support (txt2img, img2img, inpainting), support for Minicpm-4B and Yi-coder-chat, and updates for DeepSeek V2/2.5 and Qwen2 audio.

Key Highlights

  • Added comprehensive SD API support (txt2img, img2img, inpainting).
  • Added support for Minicpm-4B and Yi-coder-chat models.
  • Added support for DeepSeek V2 and V2.5 models.

New Features

  • Support qwen2-vl-instruct GPTQ format and AWQ format
  • Support minicpm-4B
  • support sdapi/txt2img
  • [UI] Auto-fill chat_template parameter on registration page
  • support sdapi/sd-models and sdapi/samplers
  • support deepseek-v2 and 2.5
  • Update Qwen2-VL-Model to support flash_attention_2 implementation
  • support sdapi/img2img
  • support flux.1 image2image and inpainting
  • Support yi-coder-chat
  • qwen2 audio

Full Release Notes

# What's new in 0.15.1 (2024-09-14)
These are the changes in inference v0.15.1.
## New features
* FEAT: Support qwen2-vl-instruct GPTQ format and AWQ format by @Jun-Howie in https://github.com/xorbitsai/inference/pull/2251
* FEAT: Support minicpm-4B by @Jun-Howie in https://github.com/xorbitsai/inference/pull/2263
* FEAT: support sdapi/txt2img by @qinxuye in https://github.com/xorbitsai/inference/pull/2248
* FEAT: [UI] Auto-fill chat_template parameter on registration page. by @yiboyasss in https://github.com/xorbitsai/inference/pull/2268
* FEAT: support sdapi/sd-models and sdapi/samplers by @qinxuye in https://github.com/xorbitsai/inference/pull/2288
* FEAT: support deepseek-v2 and 2.5 by @amumu96 in https://github.com/xorbitsai/inference/pull/2292
* FEAT: Update Qwen2-VL-Model to support flash_attention_2 implementation by @LaureatePoet in https://github.com/xorbitsai/inference/pull/2289
* FEAT: support sdapi/img2img by @qinxuye in https://github.com/xorbitsai/inference/pull/2293
* FEAT: support flux.1 image2image and inpainting by @qinxuye in https://github.com/xorbitsai/inference/pull/2296
* FEAT: Support yi-coder-chat by @Jun-Howie in https://github.com/xorbitsai/inference/pull/2302
* FEAT: qwen2 audio by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2271
## Enhancements
* ENH: Update CosyVoice Huggingface by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2249
* ENH: Supports multi functions in tool call for qwen2 by @ChengjieLi28 in https://github.com/xorbitsai/inference/pull/2265
* ENH: add `print-error` option in benchmark by @Dawnfz-Lenfeng in https://github.com/xorbitsai/inference/pull/2283
* ENH: Support fish speech 1.4 by @codingl2k1 in https://github.com/xorbitsai/inference/pull/2295
## Bug fixes
* BUG: tts stream mode not working by @leslie2046 in https://github.com/xorbitsai/inference/pull/2279
* BUG: fix issue with model launch failing when .safetensors file is missing (#2094) by @Charmnut in https://github.com/xorbitsai/inference/pull/2290
* BUG: fix sampler_name for img2img by @qinxuye in https://github.com/xorbitsai/inference/pull/2301
* BUG: modify vllm image version by @amumu96 in https://github.com/xorbitsai/inference/pull/2311
* Bug: modify vllm image version by @amumu96 in https://github.com/xorbitsai/inference/pull/2312
## Documentation
* DOC: update readme & builtin models by @qinxuye in https://github.com/xorbitsai/inference/pull/2285

## New Contributors
* @Jun-Howie made their first contribution in https://github.com/xorbitsai/inference/pull/2251
* @leslie2046 made their first contribution in https://github.com/xorbitsai/inference/pull/2279
* @Charmnut made their first contribution in https://github.com/xorbitsai/inference/pull/2290
* @LaureatePoet made their first contribution in https://github.com/xorbitsai/inference/pull/2289

**Full Changelog**: https://github.com/xorbitsai/inference/compare/v0.15.0...v0.15.1