release v1.7.1
This commit is contained in:
parent
887ba06bd6
commit
b8abd2fef3
@ -1,17 +1,31 @@
|
||||
## Changes
|
||||
|
||||
**This version includes important bug fixes, it is strongly recommended to upgrade to this version.**
|
||||
|
||||
### Upgrades
|
||||
|
||||
- rwkv 0.8.25 (fix v6 fp16i8)
|
||||
- webgpu 0.3.20 https://github.com/cgisky1980/ai00_rwkv_server
|
||||
|
||||
### Features
|
||||
|
||||
- allow setting quantizedLayers of WebGPU mode
|
||||
|
||||
### Improvements
|
||||
|
||||
- improve occurrence[token] condition
|
||||
- disable AVOID_PENALTY_TOKENS when generating (still enabled when preprocessing)
|
||||
- enable useHfMirror by default for chinese users
|
||||
|
||||
### Fixes
|
||||
|
||||
- fix /update-config can make the default value of unclearly specified fields invalid by passing in None fields
|
||||
- fix the issue where state cache could be modified leading to inconsistent hit results
|
||||
- fix convert_safetensors.py for rwkv6
|
||||
- add python3-dev to lora fine-tune dependencies (this may previously lead to the error of v5 fine-tune)
|
||||
|
||||
### Chores
|
||||
|
||||
- change AVOID_PENALTY to \n only
|
||||
- chores
|
||||
- hide MPS and CUDA-Beta Options
|
||||
- update manifest
|
||||
|
||||
## Install
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user