hsj576/GRIFFIN

Official Implementation of "GRIFFIN: Effective Token Alignment for Faster Speculative Decoding"[NeurIPS 2025]

/ 100

Experimental

No commits in the last 6 months.

Stale 6m No Package No Dependents

Maintenance 2 / 25

Adoption 6 / 25

Maturity 9 / 25

Community 9 / 25

Stars

Forks

Language

Python

License

Apache-2.0

Category

Last pushed

May 12, 2025

Commits (30d)

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/hsj576/GRIFFIN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

vitali87/speculant-graph

Graph drafts, LLM verifies: a novel speculative decoding framework

Hambaobao/HCP-Coder

Hierarchical Context Pruning (HCP): A strategy to optimize real-world code completion with...

hsj576/GTO

Official Implementation of "Bridging Draft Policy Misalignment: Group Tree Optimization for...

CyberCoder-IITM/HaloSpec

Adaptive speculative decoding benchmark with runtime perturbation and SLO-aware scoring

levvius/adaptive-speculative-decoding

Adaptive speculative decoding for LLM inference latency optimization