janhq/cortex.llamacpp

Issues

• feat: Automate e2e testing for common models in Hugging Face Cortexso Hub

  #185 opened 3 months ago by Van-QA
  0

• feat: add build cuda without any avx instruction

  #173 opened 3 months ago by nguyenhoangthuan99
  1

• Discussion: batching benchmark and improvement

  #164 opened 3 months ago by vansangpfiev
  2

• bug: CI for vulkan builds seem broken when rebase to b3389

  #143 opened 3 months ago by vansangpfiev
  0

• feat: Revamp the README.md file

  #139 opened 4 months ago by irfanpena
  0

• feat: Return logits_prob in `chat_completion`

  #135 opened 4 months ago by hiro-v
  0

• feat: improve the testing so we can rebase llama.cpp nightly

  #47 opened 4 months ago by vansangpfiev
  0

• bug: Quick start section in README.md has duplicated command

  #109 opened 4 months ago by xiangyang-95
  1

• feat: Add Intel GPU Support via SYCL on Linux platform

  #107 opened 5 months ago by xiangyang-95
  0

• feat: get running models

  #33 opened 5 months ago by vansangpfiev
  0

• feat: CI for VNNI support

  #60 opened 5 months ago by vansangpfiev
  0

• Discussion: Review cuda build flags

  #24 opened 6 months ago by vansangpfiev
  0

• feat: instructions detecting

  #20 opened 6 months ago by vansangpfiev
  0

• Codebase should have a clear coding convention

  #17 opened 6 months ago by vansangpfiev
  0

• feat: CI

  #1 opened 6 months ago by vansangpfiev
  1

• feat: example to run backend

  #2 opened 6 months ago by vansangpfiev
  0

• feat: e2e testing script for completion endpoint

  #3 opened 6 months ago by vansangpfiev
  0

• feat: e2e testing script for embedding endpoint

  #4 opened 6 months ago by vansangpfiev
  0

• feat: [Windows] CI for AMD RoCM support

  #9 opened 6 months ago by hiro-v
  0