Skip to content

Releases: josStorer/RWKV-Runner

v1.5.6

29 Nov 13:33
Compare
Choose a tag to compare

Changes (v1.5.6 is a patch for v1.5.5)

  • MIDI Input Audio Tracks (Experimental, playing tracks is not supported yet, please save to generation area to preview)
  • fix autoPlayed midi cannot be stopped
  • try to use local soundfont by default
  • improve details

Install

MIDI Input Audio Tracks

image

v1.5.5

29 Nov 11:45
Compare
Choose a tag to compare

Changes

  • MIDI Input Audio Tracks (Experimental, playing tracks is not supported yet, please save to generation area to preview)
  • fix autoPlayed midi cannot be stopped
  • try to use local soundfont by default
  • improve details

Install

MIDI Input Audio Tracks

image

v1.5.4

24 Nov 11:36
Compare
Choose a tag to compare

Changes

  • upgrade to rwkv 0.8.22 (rwkv6 support)
  • allow reading attachments even if the model is offline
  • improve launch flow of webgpu mode
  • allow safetensors converter on macOS
  • fix fs watcher of macOS
  • update defaultConfigs
  • update manifest
  • chores

Install

v1.5.3

20 Nov 16:35
Compare
Choose a tag to compare

Changes

  • add webgpu nf4
  • add sidePanel for Chat page
  • add hf-mirror for cn users
  • use local API when it's working, even if a custom API URL is provided
  • add rwkv API URL Option
  • macos: change default webgpu backend to aarch64-apple-darwin and fix the permission issue
  • strict default_stop
  • fix state_cache of deploy mode
  • fix a finetune bug
  • improve lazy loading ui
  • display lastModelName at the top (WorkHeader)
  • chores

Install

v1.5.2

09 Nov 14:24
Compare
Choose a tag to compare

v1.5.1

08 Nov 16:04
Compare
Choose a tag to compare

Changes

Features

  • add webUI for easier service sharing (enable it in Configs page or --webui command line parameter, compile it with make build-web)
  • add deployment mode. If /switch-model with deploy: true, will disable /switch-model, /exit and other dangerous APIs (state cache APIs, part of midi APIs)

Chores

  • print error.txt to console when script fails
  • api url getter

Fixes

  • set deepspeed to 0.11.2 to avoid finetune error
  • fix /docs default api params (Pydantic v2)

Install

v1.5.0

05 Nov 13:27
Compare
Choose a tag to compare

Changes

Features

  • chat attachment is now related to single message (Experimental)
  • port occupied detection

Upgrades

  • upgrade to rwkv 0.8.20

Improvements

  • improve the compatibility between frontend presets and chatgpt api
  • improve memory usage of state cache

Chores

  • update ngrok_connect
  • python38 compatibility
  • adjust startup process

Fixes

  • fix log encoding error
  • fix stop button status of Chat page

Install

v1.4.9

27 Oct 06:28
Compare
Choose a tag to compare

Changes

Features

  • allow conversation with some document (.pdf, .txt) (Experimental)
  • add /file-to-text api
  • allow avatarImg to be local absolute path
  • base64 preset support

Upgrades

  • upgrade to rwkv 0.8.16 (DirectML support; rwkv 5.2 no longer needs to ensure custom cuda kernel enabled)
  • upgrade to webgpu 0.2.2 (WebGPU Mode is now recommended for AMD and Intel Users) (https://github.com/josStorer/ai00_rwkv_server)
  • upgrade python packages

Improvements

  • improve cuda kernel compatibility (compute compatibility 5.3, Jetson Nano, MX Series, Nvidia 10 Series+)
  • RWKVType now no longer relies on the file name (use emb)
  • improve message interruption and retry for Chat page
  • update sample.jsonl of LoRA finetune
  • update api stop strategy for better custom user_name and assistant_name support
  • edited chat message now is marked as Normal
  • change default World series prefix to User/Assistant

Chores

  • update manifest.json (RWKV-5)
  • update readme and client text description
  • add pip --no-warn-script-location
  • mark rwkv raven series as old model
  • chore

Fixes

  • fix linux kernel (partial revert 68228a4)
  • fix the make command on Linux and macOS, no longer need manual operations on the wsl.go file. (#158, #173, #207)

Install

v1.4.8

03 Oct 07:21
Compare
Choose a tag to compare

v1.4.7

18 Sep 15:20
Compare
Choose a tag to compare

Changes

  • custom tokenizer .txt support
  • add pre-compiled beta cuda kernel (rwkv-beta==0.8.5, 40%+ faster for fp16) (thanks to #180, pre-compiled kernel of RTX 40 Series will be included later)

Install