Pinned Loading

1. DiskANN DiskANN Public

   Forked from microsoft/DiskANN

   Scalable graph based indices for approximate nearest neighbor search

   C++ 1

2. ranonrkm.github.io ranonrkm.github.io Public

   TeX

3. Infini-AI-Lab/MagicDec Infini-AI-Lab/MagicDec Public

   [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding

   Python 152 12

4. Infini-AI-Lab/Kinetics Infini-AI-Lab/Kinetics Public

   Kinetics: Rethinking Test-Time Scaling Laws

   Python 87 3

5. Infini-AI-Lab/MagicDec-part1 Infini-AI-Lab/MagicDec-part1 Public

   Speculative decoding for high-throughput long-context inference

   JavaScript

6. Infini-AI-Lab/MagicDec-part2 Infini-AI-Lab/MagicDec-part2 Public

   MagicDec: Breaking the Latency-Throughput Tradeoff for Long Contexts with Speculative Decoding

   JavaScript