Alternatives and similar repositories for DeFT

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

• mit-han-lab / flash-moba
  ☆187Updated last week
• RLsys-Foundation / TritonForge
  🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…
  ☆102Updated 2 weeks ago
• NonvolatileMemory / flash_tree_attn
  ☆19Updated 11 months ago
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆44Updated last year
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆47Updated last year
• attention-survey / Efficient_Attention_Survey
  A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention
  ☆233Updated 3 months ago
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆41Updated last year
• osayamenja / FlashMoE
  Distributed MoE in a Single Kernel [NeurIPS '25]
  ☆145Updated 2 months ago
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆49Updated 3 months ago
• z-lab / sparselora
  [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
  ☆60Updated 4 months ago
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆64Updated last year
• tile-ai / AttentionEngine
  ☆51Updated 6 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆108Updated 8 months ago
• SqueezeAILab / SqueezedAttention
  [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference
  ☆54Updated last year
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆51Updated 4 months ago
• tilde-research / nsa-impl
  An efficient implementation of the NSA (Native Sparse Attention) kernel
  ☆126Updated 5 months ago
• tsinghua-ideal / Twilight
  [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning
  ☆69Updated 2 weeks ago
• mit-han-lab / fastrl
  Efficient Reinforcement Learning for Language Models
  ☆43Updated last week
• metacarbon / shareAtt
  Beyond KV Caching: Shared Attention for Efficient LLMs
  ☆20Updated last year
• Jingyu6 / speculative_prefill
  ☆46Updated 6 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
• Infini-AI-Lab / Kinetics
  Kinetics: Rethinking Test-Time Scaling Laws
  ☆82Updated 4 months ago
• RLsys-Foundation / APRIL
  APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…
  ☆44Updated last month
• xdit-project / DiTCacheAnalysis
  An auxiliary project analysis of the characteristics of KV in DiT Attention.
  ☆32Updated last year
• sail-sg / LongSpec
  LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  ☆67Updated 4 months ago
• zhuzilin / flash-attention-with-sink
  ☆39Updated 3 months ago
• LiuXiaoxuanPKU / OSD
  ☆61Updated 11 months ago
• microsoft / RetrievalAttention
  Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
  ☆99Updated 2 months ago
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
  ☆59Updated last month
• svg-project / flash-kmeans
  Fast and memory-efficient exact kmeans
  ☆126Updated 2 weeks ago