M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference
Paper
•
2502.02040
•
Published
•
2
Nikhil
NickNickGo
AI & ML interests
None yet
Recent Activity
commented on
a paper
about 1 month ago
Mirror Speculative Decoding: Breaking the Serial Barrier in LLM
Inference
upvoted
a
paper
8 months ago
M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer
Inference
new activity
10 months ago
NickNickGo/pocket_olmo:Adding `safetensors` variant of this model
Organizations
None yet