Article
2x Faster on a 229B MoE: EAGLE3 Speculative Decoding for MiniMax-M2.5
•
1
Gustavo A Lujan PRO
lujangusface
AI & ML interests
None yet
Recent Activity
updated a model 1 day ago
thoughtworks/Qwen3-Coder-Next-Eagle3-exp-e published a model 1 day ago
thoughtworks/Qwen3-Coder-Next-Eagle3-exp-e updated a model 2 days ago
thoughtworks/MiniMax-M2.5-Eagle3Organizations
published an article 4 days ago
published an article 7 days ago
Article
Google Released Gemma-4 Four Days Ago. We Already Made It 1.72× Faster.
•
2
published an article 11 days ago
Article
Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs
•
6