theluyuan/RWKV-Runner
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

release v1.7.3

Browse Source
This commit is contained in:
josc146 2024-03-11 19:07:08 +08:00
parent bb1a6191b0
commit 2604d3c47b
1 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
CURRENT_CHANGE.md
View File

@ -2,16 +2,24 @@
### Features ### Features
- allow setting tokenChunkSize of WebGPU mode - add Docker support (#291) @LonghronShen
- expose global_penalty
### Fixes
- fix a generation exception caused by potentially dangerous regex being passed into the stop array
- fix max_tokens parameter of Chat page not being passed to backend
- fix the issue where penalty_decay and global_penalty are not being passed to the backend default config when running
the model through client
### Improvements ### Improvements
- improve parameters controllable range - prevent 'torch' has no attribute 'cuda' error in torch_gc, so user can use CPU or WebGPU (#302)
### Chores ### Chores
- update defaultModelConfigs - bump dependencies
- add pre-release workflow
- dep_check.py now ignores GPUtil
## Install ## Install