Changelog
v0.1.2 (24/10/2023)
Highlights
- Support Efficient Inference Engine lmdeploy turbomind
New Features
- Support Efficient Inference Engine TurboMind: Based on lmdeploy turbomind, Lagent supports the inference of LLaMA and its variant models on NVIDIA GPUs. (#47)
Contributors
A total of 2 developers contributed to this release. Thanks @Harold-lkk @jiangningliu30