Faster Text Generation with Self-Speculative Decoding
•
45
Mostafa Elhoushi
melhoushi
AI & ML interests
Make ML faster, smaller, and more accurate
Recent Activity
updated
a model
8 days ago
melhoushi/layer-skip-v1
commented
a paper
29 days ago
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
updated
a model
2 months ago
facebook/layerskip-llama2-70B
Articles
Organizations
melhoushi's activity
No public activity