Atinoda/text-generation-webui-docker

Issues

• Upgrade torch version with the README documentation version

  #58 opened 2 months ago by nicokim
  5

• v1.15 to latest tag

  #60 opened 3 months ago by robballantyne
  1

• Default Nvidia TensorRT-LLM variant v1.14 does not start

  #59 opened 3 months ago by ht-sp
  1

• default text-generation-webui:default-rocm is broken

  #57 opened 3 months ago by rshxyz
  3

• Thank you for making this, how can I use this for embeddings

  #56 opened 4 months ago by thistleknot
  1

• Update Ubuntu version to 24.04

  #52 opened 6 months ago by adamoutler
  17

• Support webui 1.13.0

  #55 opened 5 months ago by fzyzcjy
  2

• Update dependencies for getting LLAMA 3.1 to work

  #54 opened 5 months ago by reuschling
  3

• Support for arm CPUs?

  #53 opened 6 months ago by RiskierSubset
  1

• unraid app development

  #5 opened 2 years ago by Steel-skull
  18

• Can not access WebUI

  #50 opened 7 months ago by dingho
  2

• Intel Arc support

  #38 opened a year ago by Atinoda
  6

• Missing ffmpeg dependency for whisper sst

  #48 opened 8 months ago by nspitko
  1

• Alltalk_tts extension doesn't run properly?

  #49 opened 8 months ago by haxxorboi
  1

• Container instantly crashes when trying to load GGUF

  #45 opened 9 months ago by ErrickVDW
  33

• EXTRA_LAUNCH_ARGS are not honored

  #25 opened 8 months ago by jrsperry
  6

• Unable to run oobabot-plugin, missing python oobabot_plugin module

  #46 opened 9 months ago by Casuallynoted
  5

• Can't launch the UI by docker compose up

  #47 opened 9 months ago by silverwind63
  1

• Error response from daemon: could not select device driver "nvidia" with capabilities:

  #29 opened 10 months ago by dewijones92
  5

• Can't load models with CPU

  #16 opened 10 months ago by RBNXI
  7

• Cannot load exllamav2 models

  #44 opened 10 months ago by MrMojoR
  8

• load model failed

  #43 opened 10 months ago by twilight0620
  3

• AMD / ROCM support

  #27 opened a year ago by panayotovip
  12

• make settings.yaml persistent!!!

  #40 opened a year ago by Gee1111
  2

• EXTRA_LAUNCH_ARGS only accepts the fist Argument

  #42 opened a year ago by Gee1111
  0

• Apple Silicon / MacOS support

  #22 opened a year ago by tnunamak
  10

• no launch args --subpath

  #35 opened a year ago by SnowWindDancing
  2

• Error 804

  #37 opened a year ago by FieldOfRice
  1

• exec /scripts/docker-entrypoint.sh: exec format error

  #36 opened a year ago by thejacer
  2

• Unable to load coqui_tts

  #33 opened a year ago by FKouhai
  8

• Error when loading some GGUF files with llama.cpp

  #32 opened a year ago by silverwind63
  1

• No such file or directory error

  #34 opened a year ago by seyyaw
  2

• Running without a GPU

  #13 opened a year ago by Sharpz7
  9

• Trying to load EXL2 with default-nightly image fails

  #31 opened a year ago by accountForIssues
  1

• Not running Apple M1: third_party/cuda/bin/ptxas --version died with <Signals.SIGTRAP: 5>.

  #30 opened a year ago by AIWintermuteAI
  1

• New Cuda

  #28 opened a year ago by LemonRiz
  5

• Is Mistral supported on default version?

  #26 opened a year ago by jaredquekjz
  1

• exllamav2 integration?

  #23 opened a year ago by simplesisu
  2

• Unable to load GGUF model (llama-cpu-nightly)

  #21 opened a year ago by Philipp-Sc
  1

• older images?

  #18 opened a year ago by syaoran68
  2

• Where i have to upload the training-dataset?

  #19 opened a year ago by DietmarGrabowski
  5

• Auto-detected mode as 'legacy' nvidia-container-cli: initialization error: load library failed: libnvidia-ml.so.1:

  #20 opened a year ago by ianuragbhatt
  3

• Error : arrow::fs::FinalizeS3 was not called even though S3 was initialized

  #15 opened a year ago by ksingh-scogo
  3

• Nginx proxy with ssl support?

  #11 opened a year ago by ai792
  2

• Unable to Save Characters in Chat Mode

  #14 opened a year ago by czjyyds
  2

• Directories are mapped against actual windows folders instead of volumes

  #12 opened a year ago by snipercup
  2

• Training in 4-bit

  #8 opened 2 years ago by Jeduh
  15

• connection refused issue

  #7 opened 2 years ago by sdlzen
  6

• how to configure for CPU only?

  #9 opened 2 years ago by jatinsne
  1

• Incorporate exllama?

  #6 opened 2 years ago by uogbuji
  1