Trained early exit head to be used with Dynamic Self-Speculative Decoding
🤝 Open to Collab
Florian Valade
FlorianVal
AI & ML interests
Efficiency in Deep learning
Recent Activity
updated a Space 3 days ago
FlorianVal/Dssd_Demo liked a model about 1 month ago
zai-org/GLM-5.3 upvoted an article 3 months ago
Tensor Parallelism (TP) in Transformers: 5 Minutes to UnderstandOrganizations
