Noeda/rllama

Issues

• error when building server

  #17 opened a year ago by shkr
  1

• Have plan to support Q4_0 ?

  #16 opened a year ago by caofx0418
  0

• docker failed

  #15 opened a year ago by sunnyregion
  1

• will this support llama2?

  #14 opened a year ago by shenjackyuanjie
  1

• TensorError(TensorBuilderEmpty) when running program

  #8 opened 2 years ago by hydroid7
  10

• Can you load another llama base model from hugging face

  #13 opened 2 years ago by poohzaza166
  1

• load models with mmap()

  #11 opened 2 years ago by sebcmp
  0

• Consider using ArrayFire code that is portable across CUDA, OpenCL and CPU devices

  #9 opened 2 years ago by apcameron
  0

• Heads up. Doesn't build on Arch Linux due to #![feature(stdsimd)]

  #7 opened 2 years ago by trholding
  1

• Use portable simd as a backup

  #2 opened 2 years ago by trimental
  5

• Add Support for other Architectures

  #4 opened 2 years ago by apcameron
  1

• error[E0554]: `#![feature]` may not be used on the stable release channel

  #1 opened 2 years ago by Alexmakes
  1