v0.0.8
版本发布时间: 2023-09-11 23:34:23
InternLM/lmdeploy最新发布版本:v0.6.0a0(2024-08-26 17:12:19)
Highlight
- Support Baichuan2-7B-Base and Baichuan2-7B-Chat
- Support all features of Code Llama: code completion, infilling, chat / instruct, and python specialist
What's Changed
🚀 Features
- Support baichuan2-chat chat template by @wangruohui in https://github.com/InternLM/lmdeploy/pull/378
- Support codellama by @lvhan028 in https://github.com/InternLM/lmdeploy/pull/359
🐞 Bug fixes
- [Fix] when using stream is False, continuous batching doesn't work by @sleepwalker2017 in https://github.com/InternLM/lmdeploy/pull/346
- [Fix] Set max dynamic smem size for decoder MHA to support context length > 8k by @lvhan028 in https://github.com/InternLM/lmdeploy/pull/377
- Fix exceed session len core dump for chat and generate by @AllentDan in https://github.com/InternLM/lmdeploy/pull/366
- [Fix] update puyu model by @Harold-lkk in https://github.com/InternLM/lmdeploy/pull/399
📚 Documentations
- [Docs] Fix quantization docs link by @LZHgrla in https://github.com/InternLM/lmdeploy/pull/367
- [Docs] Simplify
build.mdby @pppppM in https://github.com/InternLM/lmdeploy/pull/370 - [Docs] Update lmdeploy logo by @lvhan028 in https://github.com/InternLM/lmdeploy/pull/372
New Contributors
- @sleepwalker2017 made their first contribution in https://github.com/InternLM/lmdeploy/pull/346
Full Changelog: https://github.com/InternLM/lmdeploy/compare/v0.0.7...v0.0.8