Infini-AI-Lab/Sequoia

Issues

• Work On CPU

  #16 opened 6 months ago by ZepinLi
  0

• Reproducibility: the tree_search generates too small tree

  #13 opened 6 months ago by KexinFeng
  8

• Estimate the number of generated tokens per step from the acceptance-rate-vector?

  #14 opened 6 months ago by KexinFeng
  1

• Question on tree search algorithm

  #15 opened 6 months ago by cyLi-Tiger
  3

• Is there any benchmark that compares Sequoia against vanilla speculative decoding?

  #10 opened 6 months ago by KexinFeng
  2

• How to benchmark for speedup and acceptance rate?

  #12 opened 7 months ago by singularity-s0
  7

• The support on vLLM?

  #11 opened 7 months ago by KexinFeng
  1

• Thanks for your good work.

  #9 opened 7 months ago by xwjim
  0

• data loading timing and disk use

  #4 opened 8 months ago by poedator
  0

• Integration with Lit-GPT

  #3 opened 8 months ago by tchaton
  2

• Tensor shape mismatch when computing apply_rotary_pos_emb

  #2 opened 8 months ago by Tomorrowdawn
  5

• Error `p.attn_bias_ptr is not correctly aligned` when testing

  #1 opened 8 months ago by poedator
  1