release v1.6.7

This commit is contained in:
josc146 2023-12-29 12:26:33 +08:00
parent 81544ca8b3
commit 94b3882d30

View File

@ -1,12 +1,10 @@
## Changes ## Changes
- improve refreshRemoteModels - rwkv5 lora finetune support (https://github.com/JL-er/RWKV-v5-lora)
- reduce precompiled web_rwkv_py size - improve memory usage and speed of convert_safetensors.py
- webgpu(Python) max_buffer_size (12B support) and turbo - webgpu(python) state cache support
- improve role-playing effect - improve state cache performance (especially for rwkv.cpp)
- update manifest.json (a lot of new models) - chore
- bump webgpu(ai00_server) mode to v0.3.8
- improve details
## Install ## Install