turboderp/exui

Issues

• Prompt format for Qwen?

  #67 opened a month ago by charleswg
  0

• Cuda jit_compile error

  #66 opened a month ago by charleswg
  1

• Feature request: reordering list items

  #65 opened 2 months ago by Zueuk
  0

• Dry Sampler Support

  #62 opened 2 months ago by alexbrowngh
  0

• NameError: name 'exllamav2_ext' is not defined

  #61 opened 3 months ago by jwax33
  5

• Continue has a race

  #60 opened 4 months ago by IMbackK
  0

• Model download URLs?

  #59 opened 4 months ago by SoftologyPro
  1

• Notepad: generate and token buttons disabled before writeing something in the context

  #58 opened 4 months ago by IMbackK
  2

• Determinism

  #57 opened 4 months ago by IMbackK
  2

• exui not able to connect to server from Win10 browser - WSL2 Debian

  #28 opened a year ago by mindkrypted
  1

• CUDA_HOME variable not set

  #38 opened 8 months ago by EidosL
  4

• gguf models

  #56 opened 5 months ago by DjagbleyEmmanuel
  2

• UI Loads to a blank grey screen

  #55 opened 6 months ago by fake-name
  1

• Running server from different folder raises Internal Server Error.

  #54 opened 6 months ago by fatality14
  1

• server.py won't open

  #53 opened 7 months ago by ReMeDy-TV
  1

• Launching throws error with Exllamav2 stating "Tokenizers" are not found

  #47 opened 7 months ago by Adzeiros
  2

• Windows 11 install procedure and missing dependancies (transformers)

  #31 opened 10 months ago by Anon426
  2

• DLL load failed while importing exllamav2_ext

  #40 opened 8 months ago by jagerius
  2

• Out of memory

  #46 opened 8 months ago by AICodingTester
  16

• Permit setting default promt format and max tokens in models tab

  #50 opened 7 months ago by dagbdagb
  0

• Add tooltip to briefly explain the parameters in chat tab

  #51 opened 7 months ago by dagbdagb
  0

• Feature request - Colorized Code Markup

  #49 opened 7 months ago by chaincrafter
  0

• Answer does not escape HTML tags

  #41 opened 7 months ago by chaincrafter
  2

• Edit context

  #43 opened 7 months ago by dagbdagb
  3

• `exui` doesn't escape HTML tags in user input.

  #32 opened 10 months ago by andrewgross
  3

• how to name the sessions?

  #45 opened 8 months ago by Fuckingnameless
  4

• VRAM Usage

  #39 opened 8 months ago by ec111
  5

• Client-side "save to file"-function for code output?

  #42 opened 8 months ago by dagbdagb
  1

• how to set Q4 cache on?

  #44 opened 8 months ago by Fuckingnameless
  0

• ImportError: DLL load failed while importing exllamav2_ext: The specified procedure could not be found.

  #37 opened 9 months ago by Zueuk
  0

• "copy text" button in code ouput windows?

  #36 opened 9 months ago by dagbdagb
  3

• Make text field compatible with the LanguageTool browser extension.

  #35 opened 9 months ago by brucethemoose
  2

• ninja: build stopped: subcommand failed.

  #34 opened 9 months ago by kurugai
  2

• Not finding CUDA when it's installed both in conda env and for Windows globally (different versions)

  #26 opened a year ago by ewebgh33
  10

• Multiple Roles wont answer or interogate with each other.

  #30 opened 10 months ago by chaincrafter
  2

• Pasting several lines of text into the notepad creates way too many copies of the new notepad

  #15 opened a year ago by Zueuk
  6

• Error "architectures"

  #29 opened a year ago by Gyramuur
  2

• How to increase max_tokens to 4096

  #23 opened a year ago by xldistance
  2

• Issues with window management (CachyOS / Arch)

  #27 opened a year ago by JakeSSRN
  0

• Error answering question, AssertionError: filter excludes all tags

  #25 opened a year ago by xldistance
  0

• Will this ever have a mobile version?

  #24 opened a year ago by lovee333
  0

• An option to NOT open the browser on startup?

  #14 opened a year ago by Zueuk
  1

• KeyError: '<ï½\x9cendâ\x96\x81ofâ\x96\x81sentenceï½\x9c>' Tokenizer crash

  #22 opened a year ago by SinanAkkoyun
  0

• Speculative Decoding slower (only in ExUI)

  #20 opened a year ago by SinanAkkoyun
  3

• Auto load on multi gpus

  #19 opened a year ago by wangyu1997
  2

• build error

  #18 opened a year ago by deeeed
  2

• vllm backend?

  #17 opened a year ago by ekg
  1

• Insufficient VRAM for model and cache

  #11 opened a year ago by dagbdagb
  3

• Cant point to the model dir

  #8 opened a year ago by RecoveredApparatus
  3

• Colab installion failed

  #7 opened a year ago by RecoveredApparatus
  2