Repositories list

• vortex_torch

  Public

  Infini-AI-Lab/vortex_torch’s past year of commit activity
  Vortex: A Flexible and Efficient Sparse Attention Framework

  sparsesparse-attentionllm+ 1

  sparsesparse-attentionllmllm-inference

  Python

  •

  Apache License 2.0

  •55 forks•5151 stars•00 issues•11 pull request•Updated Apr 20, 2026Apr 20, 2026

• STEM

  Public

  Infini-AI-Lab/STEM’s past year of commit activity
  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •22 forks•6565 stars•33 issues•00 pull requests•Updated Apr 20, 2026Apr 20, 2026

• WWW.Serve

  Public
  Python

  •

  Apache License 2.0

  •00 forks•11 star•00 issues•00 pull requests•Updated Mar 24, 2026Mar 24, 2026

• lm-eval-stem

  Public

  Infini-AI-Lab/lm-eval-stem’s past year of commit activity
  Python

  •

  MIT License

  •00 forks•00 stars•00 issues•00 pull requests•Updated Mar 22, 2026Mar 22, 2026

• MonarchRT

  Public
  Python

  •

  Apache License 2.0

  •1313 forks•128128 stars•00 issues•00 pull requests•Updated Feb 17, 2026Feb 17, 2026

• jackpot

  Public
  A rejection-sampling based distribution alignment method for extreme actor-policy mismatch RL Training

  rloff-policy

  rloff-policy

  Python

  •

  Apache License 2.0

  •11 fork•1515 stars•00 issues•55 pull requests•Updated Feb 11, 2026Feb 11, 2026

• jpt_website

  Public

  Infini-AI-Lab/jpt_website’s past year of commit activity
  Host the website of project Jackpot

  HTML

  •00 forks•00 stars•00 issues•00 pull requests•Updated Feb 9, 2026Feb 9, 2026

• jackpot_unofficial

  Public

  Infini-AI-Lab/jackpot_unofficial’s past year of commit activity
  00 forks•00 stars•00 issues•00 pull requests•Updated Dec 7, 2025Dec 7, 2025

• vortex-technical-blog

  Public

  Infini-AI-Lab/vortex-technical-blog’s past year of commit activity
  HTML

  •00 forks•00 stars•00 issues•00 pull requests•Updated Dec 1, 2025Dec 1, 2025

• ai-environment-architect

  Public

  Infini-AI-Lab/ai-environment-architect’s past year of commit activity
  HTML

  •00 forks•00 stars•00 issues•00 pull requests•Updated Nov 26, 2025Nov 26, 2025

• FCV

  Public
  [ACL'26 Main] When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?

  Python

  •00 forks•1212 stars•00 issues•00 pull requests•Updated Nov 4, 2025Nov 4, 2025

• M2PO

  Public
  Python

  •

  Apache License 2.0

  •44 forks•2929 stars•33 issues•00 pull requests•Updated Oct 8, 2025Oct 8, 2025

• Multiverse

  Public
  Python

  •

  Apache License 2.0

  •1010 forks•115115 stars•55 issues•00 pull requests•Updated Sep 13, 2025Sep 13, 2025

• OLMo

  Public
  Modeling, training, eval, and inference code for OLMo

  Python

  •

  Apache License 2.0

  •751751 forks•00 stars•00 issues•00 pull requests•Updated Sep 10, 2025Sep 10, 2025

• Kinetics

  Public
  Kinetics: Rethinking Test-Time Scaling Laws

  Python

  •33 forks•8787 stars•00 issues•00 pull requests•Updated Jul 11, 2025Jul 11, 2025

• sglang

  Public
  SGLang is a fast serving framework for large language models and vision language models.

  Python

  •

  Apache License 2.0

  •5.5k5.5k forks•00 stars•00 issues•00 pull requests•Updated Jul 9, 2025Jul 9, 2025

• GRESO

  Public
  Python

  •77 forks•7878 stars•11 issue•00 pull requests•Updated Jun 28, 2025Jun 28, 2025

• gsm_infinite

  Public
  Python

  •44 forks•6363 stars•33 issues•00 pull requests•Updated Jun 12, 2025Jun 12, 2025

• Kinetics-PR

  Public
  Kinetics: Rethinking Test-Time Scaling Laws

  JavaScript

  •00 forks•00 stars•00 issues•00 pull requests•Updated Jun 4, 2025Jun 4, 2025

• UMbreLLa

  Public
  LLM Inference on consumer devices

  offloadingllm-inferencespeculative-decoding

  offloadingllm-inferencespeculative-decoding

  Python

  •

  Apache License 2.0

  •1515 forks•130130 stars•1212 issues•99 pull requests•Updated Mar 17, 2025Mar 17, 2025

• APE-Page

  Public
  JavaScript

  •00 forks•00 stars•00 issues•00 pull requests•Updated Feb 12, 2025Feb 12, 2025

• APE

  Public
  Python

  •66 forks•3636 stars•22 issues•00 pull requests•Updated Feb 12, 2025Feb 12, 2025

• RULER

  Public
  This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

  Python

  •

  Apache License 2.0

  •125125 forks•00 stars•00 issues•00 pull requests•Updated Jan 30, 2025Jan 30, 2025

• Sequoia

  Public
  scalable and robust tree-based speculative decoding algorithm

  efficiencyinferencellm+ 1

  efficiencyinferencellmspeculative-decoding

  Python

  •3737 forks•377377 stars•77 issues•33 pull requests•Updated Jan 28, 2025Jan 28, 2025

• lm-evaluation-harness

  Public
  A framework for few-shot evaluation of language models.

  Python

  •

  MIT License

  •3.2k3.2k forks•00 stars•00 issues•00 pull requests•Updated Jan 11, 2025Jan 11, 2025

• S2FT

  Public
  Python

  •44 forks•1919 stars•22 issues•00 pull requests•Updated Jan 3, 2025Jan 3, 2025

• S2FT-Page

  Public
  JavaScript

  •00 forks•00 stars•00 issues•00 pull requests•Updated Dec 30, 2024Dec 30, 2024

• MagicPIG

  Public
  [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation

  decodinglsh-algorithmllm-inference+ 1

  decodinglsh-algorithmllm-inferencegpu-cpu

  Python

  •

  Apache License 2.0

  •1919 forks•253253 stars•1212 issues•11 pull request•Updated Dec 16, 2024Dec 16, 2024

• MagicDec

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

  Python

  •

  Apache License 2.0

  •1212 forks•146146 stars•88 issues•00 pull requests•Updated Dec 4, 2024Dec 4, 2024

• MagicPIG-Page

  Public
  JavaScript

  •11 fork•00 stars•00 issues•00 pull requests•Updated Dec 2, 2024Dec 2, 2024