Alternatives and similar repositories for Kinetics

Users that are interested in Kinetics are comparing it to the libraries listed below

• tilde-research / nsa-impl
  An efficient implementation of the NSA (Native Sparse Attention) kernel
  ☆128Updated 6 months ago
• Infini-AI-Lab / GRESO
  ☆72Updated 6 months ago
• PKU-ML / LongPPL
  Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"
  ☆107Updated 3 months ago
• PiotrNawrot / sparse-frontier
  The evaluation framework for training-free sparse attention in LLMs
  ☆108Updated 3 months ago
• sail-sg / SkyLadder
  The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
  ☆41Updated 2 weeks ago
• Leooyii / LCEG
  Long Context Extension and Generalization in LLMs
  ☆62Updated last year
• sustcsonglin / linear-attention-and-beyond-slides
  ☆103Updated 10 months ago
• ylsung / rsq
  Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"
  ☆20Updated 7 months ago
• Infini-AI-Lab / gsm_infinite
  ☆61Updated 7 months ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆52Updated last year
• sail-sg / LongSpec
  LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  ☆73Updated 5 months ago
• Dao-AILab / grouped-latent-attention
  ☆133Updated 7 months ago
• UNITES-Lab / MC-SMoE
  [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
  ☆103Updated 6 months ago
• OpenSparseLLMs / Linear-MoE
  ☆126Updated 7 months ago
• Infini-AI-Lab / Multiverse
  ☆109Updated 4 months ago
• jxiw / M1
  M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models
  ☆47Updated 5 months ago
• OpenSparseLLMs / Linearization
  ☆62Updated 6 months ago
• Anonymous1252022 / Megatron-DeepSpeed
  ☆15Updated last year
• deep-spin / adasplash
  AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)
  ☆32Updated 3 months ago
• TianjinYellow / StableSPAM
  ☆27Updated 9 months ago
• thu-ml / ReMoE
  [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.
  ☆104Updated last year
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆43Updated last year
• hdong920 / GRIFFIN
  ☆39Updated last year
• CASE-Lab-UMD / Unified-MoE-Compression
  The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
  ☆88Updated 9 months ago
• shawntan / stickbreaking-attention
  Stick-breaking attention
  ☆62Updated 6 months ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆87Updated last year
• sail-sg / scaling-with-vocab
  [NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623
  ☆89Updated last year
• AkideLiu / MiniCache
  ☆11Updated last year
• Parallel-Reasoning / APR
  [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models
  ☆136Updated 3 weeks ago
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …
  ☆60Updated last year