speculative-decoding
Enhances LLM inference speed and reduces latency using speculative decoding techniques for real-time applications.
Install this skill
or
speculative-decoding3 files
Comments
Sign in to leave a comment.
No comments yet. Be the first to comment!
GitHub Stars 508
Rate this skill
Categorydevelopment
UpdatedMay 21, 2026
Dicklesworthstone/pi_agent_rust