Article
Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs
•
8
Zhukov
Geximus
·
AI & ML interests
None yet
Recent Activity
new activity 5 days ago
MiniMaxAI/MiniMax-M2.7:Prevent whitespace leakage in beginning of prompt new activity 23 days ago
demon-zombie/MiniMax-M2.7-AWQ-4bit:These are NOT actual AWQ-quantized models.Organizations
None yet
upvoted an article 16 days ago
upvoted an article 25 days ago
Article
2x Faster on a 229B MoE: EAGLE3 Speculative Decoding for MiniMax-M2.5
•
3
upvoted a collection 8 months ago