v0.13.1
版本发布时间: 2024-07-10 09:21:08
TabbyML/tabby最新发布版本:nightly(2023-09-08 09:39:25)
⚠️ Notice
- This is a patch release, please also check the full release note for 0.13.
🧰 Fixed and Improvements
- Bump llama.cpp version to b3334, supporting Deepseek V2 series models.
- Turn on fast attention for Qwen2-1.5B model to fix the quantization error.
- Properly set number of GPU layers (to zero) when device is CPU.
1、 tabby_aarch64-apple-darwin.zip 22.76MB
2、 tabby_x86_64-manylinux2014-cuda117.zip 119.82MB
3、 tabby_x86_64-manylinux2014-cuda122.zip 118.97MB
4、 tabby_x86_64-manylinux2014-vulkan.zip 27.84MB
5、 tabby_x86_64-manylinux2014.zip 27.81MB
6、 tabby_x86_64-windows-msvc-cuda117.zip 113.11MB
7、 tabby_x86_64-windows-msvc-cuda122.zip 112.34MB
8、 tabby_x86_64-windows-msvc-vulkan.zip 21.48MB
9、 tabby_x86_64-windows-msvc.zip 21.48MB