Alternatives and similar repositories for specreason

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

• OpenSparseLLMs / Linear-MoE
  ☆120Updated 6 months ago
• mutonix / pyramidinfer
  ☆49Updated last year
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆38Updated 9 months ago
• Jingyu6 / speculative_prefill
  ☆47Updated 6 months ago
• FFY0 / AdaKV
  The Official Implementation of Ada-KV [NeurIPS 2025]
  ☆116Updated last week
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆48Updated 4 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆155Updated last month
• sail-sg / LongSpec
  LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  ☆68Updated 4 months ago
• 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
  ☆42Updated last year
• mit-han-lab / fastrl
  [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
  ☆73Updated last week
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆60Updated 9 months ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆52Updated last year
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆108Updated 8 months ago
• OpenSparseLLMs / Linearization
  ☆61Updated 4 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"
  ☆99Updated 5 months ago
• TemporaryLoRA / Block-Attention
  ☆41Updated 8 months ago
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆47Updated last year
• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆52Updated last year
• uservan / speculative_thinking
  ☆30Updated last month
• LiuXiaoxuanPKU / OSD
  ☆63Updated last year
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆275Updated 3 weeks ago
• BaohaoLiao / RSD
  [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.
  ☆52Updated 7 months ago
• henryzhongsc / longctx_bench
  Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…
  ☆86Updated 9 months ago
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆175Updated 2 months ago
• cat538 / SKVQ
  [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
  ☆24Updated last year
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆212Updated 9 months ago
• hdong920 / LESS
  ☆53Updated last year
• NonvolatileMemory / flash_tree_attn
  ☆19Updated 11 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆132Updated last month