Alternatives and similar repositories for dkernel

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

• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆52Updated last year
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆113Updated 9 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆91Updated last year
• sail-sg / VocabularyParallelism
  Vocabulary Parallelism
  ☆24Updated 10 months ago
• IST-DASLab / SparseFinetuning
  Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
  ☆42Updated 2 years 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
• linfeng93 / BiTA
  An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.
  ☆26Updated 9 months ago
• Infini-AI-Lab / vortex_torch
  Vortex: A Flexible and Efficient Sparse Attention Framework
  ☆43Updated this week
• Infini-AI-Lab / gsm_infinite
  ☆61Updated 7 months ago
• OpenNLPLab / LASP
  Linear Attention Sequence Parallelism (LASP)
  ☆88Updated last year
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆39Updated 11 months ago
• raymin0223 / fast_robust_early_exit
  Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)
  ☆65Updated last year
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆136Updated last year
• Dao-AILab / grouped-latent-attention
  ☆133Updated 7 months ago
• wdlctc / mini-s
  ☆53Updated last year
• leloykun / flash-attention-minimal
  Flash Attention in 300-500 lines of CUDA/C++
  ☆36Updated 4 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆175Updated last year
• SalesforceAIResearch / GemFilter
  ☆85Updated 2 months ago
• rayleizhu / vllm-ra
  [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts
  ☆40Updated last year
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆79Updated last year
• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆54Updated last year
• PiotrNawrot / sparse-frontier
  The evaluation framework for training-free sparse attention in LLMs
  ☆108Updated 3 months ago
• FasterDecoding / TEAL
  ☆156Updated 11 months ago
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆64Updated last year
• Leooyii / LCEG
  Long Context Extension and Generalization in LLMs
  ☆62Updated last year
• IST-DASLab / RoSA
  Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)
  ☆44Updated last year
• zankner / Hydra
  ☆51Updated last year
• princeton-pli / PruLong
  Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"
  ☆47Updated 5 months ago
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆146Updated last year
• Jingyu6 / speculative_prefill
  ☆49Updated 7 months ago