PyPI page
Home page
Author:
License:
Summary:
Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Latest version:
0.1
Required dependencies:
accelerate
|
fschat
|
protobuf
|
sentencepiece
|
torch
|
transformers
Optional dependencies:
bitsandbytes
|
scipy
|
wandb
Downloads last day:
1
Downloads last week:
115
Downloads last month:
166