release v1.4.5
This commit is contained in:
parent
87b2c3ed7d
commit
e0df9ae47b
@ -1,10 +1,14 @@
|
|||||||
## Changes
|
## Changes
|
||||||
|
|
||||||
- webgpu support (AMD, Intel, Nvidia, Apple)
|
- frontend: update manifest (a lot of new models)
|
||||||
- add rwkv-cuda-beta support (faster)
|
- frontend: correct Preset UI description
|
||||||
- add misc API (`/models` and `/dashboard/billing/credit_grants`)
|
- frontend: add HardwareMonitor (Windows Only)
|
||||||
- allow multiple systems
|
- lora finetune: fix max_epochs (#170)
|
||||||
- allow completions input to be null
|
- python-backend: allow message content to be empty
|
||||||
|
- python-backend: extra ChatCompletionBody params (`raw`, `presystem`)
|
||||||
|
- python-backend: add default_stop when stop is null
|
||||||
|
- webgpu: fix webgpu_server file permissions of linux and macos
|
||||||
|
- chore
|
||||||
|
|
||||||
## Install
|
## Install
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user