v0.12.1
版本发布时间: 2024-06-14 17:31:32
xorbitsai/inference最新发布版本:v0.15.0(2024-09-06 16:45:31)
What's new in 0.12.1 (2024-06-14)
These are the changes in inference v0.12.1.
New features
- FEAT: qwen2-instruct support tool call by @ayhhyhh in https://github.com/xorbitsai/inference/pull/1631
- FEAT: Added a method to download models from csghub. by @hainaweiben in https://github.com/xorbitsai/inference/pull/1627
- FEAT: glm4-chat support tool call by @codingl2k1 in https://github.com/xorbitsai/inference/pull/1617
- FEAT: [UI] Supports viewing and deleting cache data. by @yiboyasss in https://github.com/xorbitsai/inference/pull/1637
Enhancements
- ENH: modelscope for audio models by @Minamiyama in https://github.com/xorbitsai/inference/pull/1607
- ENH: Supports
generate
interface for continuous batching by @ChengjieLi28 in https://github.com/xorbitsai/inference/pull/1621 - ENH: quantization for glm-4v by @Minamiyama in https://github.com/xorbitsai/inference/pull/1610
Bug fixes
- BUG: Fix wheel package missing thirdparty ChatTTS by @codingl2k1 in https://github.com/xorbitsai/inference/pull/1606
- BUG: fix XINFERENCE_MODEL_SRC behavior by @LukeWang-Plus in https://github.com/xorbitsai/inference/pull/1616
- BUG: Filtering Step for Streaming Responses to Qwen's Tool Calls when using vLLM by @zhanghx0905 in https://github.com/xorbitsai/inference/pull/1598
Others
- Remove selected cache models by @hainaweiben in https://github.com/xorbitsai/inference/pull/1613
New Contributors
- @LukeWang-Plus made their first contribution in https://github.com/xorbitsai/inference/pull/1616
- @ayhhyhh made their first contribution in https://github.com/xorbitsai/inference/pull/1631
Full Changelog: https://github.com/xorbitsai/inference/compare/v0.12.0...v0.12.1