sozercan/aikit

Issues

• [REQ] add vllm backend

  #418 opened a month ago by sozercan
  0

• [REQ] auto merge dependabot prs

  #416 opened a month ago by sozercan
  0

• [REQ] add flux models to the image

  #387 opened 3 months ago by sozercan
  0

• [REQ] add prebuilt prompt templates to build-args

  #277 opened 4 months ago by sozercan
  2

• [REQ] Avoid GitHub Actions cache API throttling

  #363 opened 4 months ago by sozercan
  0

• [REQ] clean up /var/lib/dpkg/status

  #337 opened 4 months ago by sozercan
  0

• [REQ] Is it possible to use optimized llama.cpp from amperecomputing?

  #327 opened 5 months ago by phirestalker
  0

• [REQ] github action

  #325 opened 5 months ago by sozercan
  0

• [REQ] replace oras image

  #316 opened 5 months ago by sozercan
  0

• [REQ] support for models from oci artifacts

  #241 opened 6 months ago by sozercan
  2

• [DOC] add contributing doc for development

  #303 opened 6 months ago by sozercan
  0

• [REQ] update helm chart security

  #297 opened 6 months ago by sozercan
  0

• [BUG] webui stops responding

  #269 opened 6 months ago by sozercan
  2

• [REQ] interactive chat interface

  #160 opened 9 months ago by sozercan
  1

• [REQ] add versioned docs

  #294 opened 6 months ago by sozercan
  0

• [REQ] arm support

  #67 opened 6 months ago by renatokeys
  1

• [REQ] Add support for phi-3 mini model

  #209 opened 7 months ago by surenderssm
  3

• [REQ] add aikit to hf local apps

  #264 opened 6 months ago by sozercan
  0

• [BUG] exllama.py: missing port in address

  #94 opened 6 months ago by sozercan
  0

• Please add a code completion model?

  #236 opened 6 months ago by ilyanoskov
  4

• [REQ] update kubernetes docs with chart url

  #246 opened 6 months ago by sozercan
  0

• [REQ] automate updating pre-made models table when a new model is published

  #250 opened 6 months ago by sozercan
  0

• [REQ] update unsloth to may 2024 release

  #235 opened 6 months ago by sozercan
  1

• [REQ] helm chart

  #219 opened 6 months ago by sozercan
  2

• [REQ] auto detect runtime for an inference container

  #181 opened 6 months ago by sozercan
  2

• [REQ] migrate from pip to uv

  #144 opened 6 months ago by sozercan
  0

• [REQ] kubernetes workflow

  #220 opened 7 months ago by sozercan
  0

• [REQ] finetune wsl2 support

  #216 opened 7 months ago by sozercan
  0

• [REQ] fine tune support for more dataset types

  #214 opened 7 months ago by sozercan
  0

• [REQ] fine tune output to exl2 or awq

  #213 opened 7 months ago by sozercan
  0

• [REQ] docs on how to add a new premade model

  #211 opened 7 months ago by sozercan
  0

• [REQ] update unsloth to llama3 release

  #199 opened 7 months ago by sozercan
  1

• [REQ] support for finetuning

  #124 opened 8 months ago by sozercan
  0

• [BUG] grpc service not ready

  #155 opened 9 months ago by Toinoux38
  2

• [REQ] code llama2

  #123 opened 10 months ago by c-nv-s
  4

• [REQ] integrate copa to auto patch model images

  #66 opened 10 months ago by sozercan
  0

• [REQ] release should trigger model update

  #73 opened a year ago by sozercan
  0

• [REQ] create status.d metadata files for llama backend cuda images

  #68 opened a year ago by sozercan
  0

• [BUG] Got a connection error when I send a request

  #53 opened a year ago by lordofthejars
  2

• [BUG] no galleries to load

  #41 opened a year ago by that1guy
  8

• [REQ] update to localai 2.0

  #21 opened a year ago by sozercan
  0