Alternatives and similar repositories for LongSpec

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

• OpenSparseLLMs / Linear-MoE
  ☆129Updated 7 months ago
• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆55Updated last year
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆52Updated last year
• hdong920 / LESS
  ☆53Updated last year
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
  ☆61Updated 3 months ago
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆39Updated 11 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 7 months ago
• Jingyu6 / speculative_prefill
  ☆50Updated 8 months ago
• hdong920 / GRIFFIN
  ☆39Updated last year
• Dominic789654 / LongGenBench
  Source code for the paper "LongGenBench: Long-context Generation Benchmark"
  ☆24Updated last year
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆44Updated last year
• SqueezeAILab / SqueezedAttention
  [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference
  ☆56Updated last year
• PKU-ML / LongPPL
  Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"
  ☆110Updated 3 months ago
• 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 10 months ago
• OpenSparseLLMs / MoM
  ☆118Updated 4 months ago
• Infini-AI-Lab / Kinetics
  Kinetics: Rethinking Test-Time Scaling Laws
  ☆85Updated 6 months ago
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆48Updated last year
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆61Updated 11 months ago
• Infini-AI-Lab / Multiverse
  ☆110Updated 4 months ago
• AkideLiu / MiniCache
  ☆11Updated last year
• NJUNLP / MCSD
  Multi-Candidate Speculative Decoding
  ☆39Updated last year
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆288Updated 2 months ago
• FFY0 / AdaKV
  The Official Implementation of Ada-KV [NeurIPS 2025]
  ☆125Updated 2 months ago
• mutonix / pyramidinfer
  ☆49Updated last year
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆109Updated 10 months ago
• VITA-Group / Ms-PoE
  "Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding" Zhenyu Zhang, Runjin Chen, Shiw…
  ☆31Updated last year
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆113Updated 10 months ago
• thu-wyz / inference_scaling
  ☆78Updated 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
• OpenSparseLLMs / Linearization
  ☆63Updated 6 months ago