Skip to content
@Infini-AI-Lab

Infini-AI-Lab

Next Generation AI algorithms and systems

Popular repositories Loading

  1. Sequoia Sequoia Public

    scalable and robust tree-based speculative decoding algorithm

    Python 322 36

  2. TriForce TriForce Public

    [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

    Python 236 13

  3. MagicPIG MagicPIG Public

    MagicPIG: LSH Sampling for Efficient LLM Generation

    Python 137 6

  4. MagicDec MagicDec Public

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

    Python 100 4

  5. Sirius Sirius Public

    Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its efficiency gain.

    Python 20 4

  6. S2FT S2FT Public

    Python 8 2

Repositories

Showing 10 of 13 repositories
  • MagicPIG Public

    MagicPIG: LSH Sampling for Efficient LLM Generation

    Infini-AI-Lab/MagicPIG’s past year of commit activity
    Python 137 Apache-2.0 6 2 0 Updated Dec 16, 2024
  • S2FT-Page Public
    Infini-AI-Lab/S2FT-Page’s past year of commit activity
    JavaScript 0 0 0 0 Updated Dec 10, 2024
  • S2FT Public
    Infini-AI-Lab/S2FT’s past year of commit activity
    Python 8 2 0 0 Updated Dec 9, 2024
  • MagicDec Public

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

    Infini-AI-Lab/MagicDec’s past year of commit activity
    Python 100 Apache-2.0 4 6 0 Updated Dec 4, 2024
  • MagicPIG-Page Public Forked from Infini-AI-Lab/Sequoia-Page
    Infini-AI-Lab/MagicPIG-Page’s past year of commit activity
    JavaScript 0 1 0 0 Updated Dec 2, 2024
  • Factor Public
    Infini-AI-Lab/Factor’s past year of commit activity
    1 0 0 0 Updated Nov 7, 2024
  • MagicDec-part1 Public

    Speculative decoding for high-throughput long-context inference

    Infini-AI-Lab/MagicDec-part1’s past year of commit activity
    JavaScript 0 Apache-2.0 0 0 0 Updated Sep 10, 2024
  • Sirius Public

    Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its efficiency gain.

    Infini-AI-Lab/Sirius’s past year of commit activity
    Python 20 4 0 0 Updated Sep 10, 2024
  • MagicDec-part2 Public

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

    Infini-AI-Lab/MagicDec-part2’s past year of commit activity
    JavaScript 0 Apache-2.0 0 0 0 Updated Sep 5, 2024
  • TriForce Public

    [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

    Infini-AI-Lab/TriForce’s past year of commit activity
    Python 236 13 7 (5 issues need help) 0 Updated Aug 31, 2024
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…