Alternatives and similar repositories for FlowSpec

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

• Jikai0Wang / OPT-Tree
  ☆28Updated 8 months ago
• ASISys / AdaSkip
  AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
  ☆20Updated last year
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆49Updated 6 months ago
• sspec-project / SparseSpec
  Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
  ☆88Updated 2 months ago
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆52Updated 6 months ago
• wln20 / CSKV
  [NeurIPS ENLSP Workshop'24] CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
  ☆16Updated last year
• Supercomputing-System-AI-Lab / MiLo
  Code repo for efficient quantized MoE inference with mixture of low-rank compensators
  ☆31Updated 9 months ago
• UNITES-Lab / C2R-MoE
  [NAACL'25 🏆 SAC Award] Official code for "Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert…
  ☆14Updated last year
• uservan / speculative_thinking
  ☆32Updated 3 months ago
• amazon-science / piperag
  PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)
  ☆30Updated last year
• ArminAzizi98 / LaMDA
  ☆15Updated last year
• microsoft / chunk-attention
  ☆85Updated 9 months ago
• haiduo / Jakiro
  This repository is the official implementation of "Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE"
  ☆36Updated 4 months ago
• zhang677 / PCL-lite
  Code for "Adaptive Self-improvement LLM Agentic System for ML Library Development" (ICML 2025)
  ☆15Updated last month
• Jingyu6 / speculative_prefill
  ☆53Updated 8 months ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆52Updated last year
• FFY0 / AdaKV
  The Official Implementation of Ada-KV [NeurIPS 2025]
  ☆126Updated 2 months ago
• Infini-AI-Lab / APE
  ☆36Updated last year
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆40Updated last year
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆69Updated last year
• mit-han-lab / fastrl
  [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
  ☆131Updated 2 months ago
• yangyifei729 / KVSharer
  Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''
  ☆31Updated last year
• NoakLiu / PiKV
  PiKV: KV Cache Management System for Mixture of Experts [Efficient ML System]
  ☆48Updated 3 months ago
• sail-sg / VocabularyParallelism
  Vocabulary Parallelism
  ☆25Updated 11 months ago
• skylight-org / sparse-attention-hub
  Advancing the frontier of efficient AI
  ☆53Updated last week
• LLMkvsys / rethink-kv-compression
  ☆22Updated 11 months ago
• SqueezeAILab / SqueezedAttention
  [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference
  ☆56Updated last year
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆147Updated last month
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆160Updated 4 months ago
• Hanchenli / vllm-continuum
  Preview Code for Continuum Paper
  ☆35Updated 2 weeks ago