MagicDec: Breaking the Latency-Throughput Tradeoff for Long Contexts with Speculative Decoding
-
Notifications
You must be signed in to change notification settings - Fork 0
MagicDec: Breaking the Latency-Throughput Tradeoff for Long Contexts with Speculative Decoding
License
Infini-AI-Lab/MagicDec-part2
About
MagicDec: Breaking the Latency-Throughput Tradeoff for Long Contexts with Speculative Decoding
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published