MDK8888/GPTFast
Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.
75 best points · 15 comments · 1 Hacker News post · 685 GitHub stars · View on GitHub
Hacker News discussions
- A Python Library to 6-7x the inference speed of your HF models (75 points, 15 comments, by MDK8888, 2024-02-22)