Alternatives and similar repositories for decoding-speculative-decoding

Users that are interested in decoding-speculative-decoding are comparing it to the libraries listed below

• FasterDecoding / TEAL
  ☆157Updated 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
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆136Updated last year
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆176Updated last year
• SqueezeAILab / SqueezedAttention
  [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference
  ☆55Updated last year
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆52Updated 5 months ago
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆39Updated 11 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆113Updated 10 months ago
• ScalingIntelligence / CATS
  ☆31Updated last year
• 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
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆147Updated 3 weeks ago
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆44Updated last year
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆48Updated last year
• kssteven418 / SqueezeLLM-gradients
  ☆21Updated last year
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆52Updated last year
• linfeng93 / BiTA
  An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.
  ☆26Updated 9 months ago
• IST-DASLab / HALO
  HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…
  ☆29Updated 11 months ago
• hahnyuan / ASVD4LLM
  Activation-aware Singular Value Decomposition for Compressing Large Language Models
  ☆84Updated last year
• OpenBitSys / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆132Updated last year
• ClubieDong / QAQ-KVCacheQuantization
  QAQ: Quality Adaptive Quantization for LLM KV Cache
  ☆55Updated last year
• SNU-ARC / any-precision-llm
  [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
  ☆123Updated 6 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆109Updated 9 months ago
• microsoft / chunk-attention
  ☆84Updated 9 months ago
• yangyifei729 / KVSharer
  Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''
  ☆31Updated last year
• NJUNLP / MCSD
  Multi-Candidate Speculative Decoding
  ☆39Updated last year
• hdong920 / GRIFFIN
  ☆39Updated last year
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆91Updated last year
• Jingyu6 / speculative_prefill
  ☆49Updated 8 months ago
• VITA-Group / llm-kick
  [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.
  ☆26Updated 9 months ago
• rayleizhu / vllm-ra
  [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts
  ☆40Updated last year