Alternatives and similar repositories for DeFT:

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

• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆26Updated 2 months ago
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆45Updated 5 months ago
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆36Updated 3 weeks ago
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]
  ☆34Updated 3 weeks ago
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆48Updated 6 months ago
• LiuXiaoxuanPKU / OSD
  ☆49Updated 5 months ago
• Jingyu6 / speculative_prefill
  ☆28Updated last month
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆91Updated last month
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆45Updated 6 months ago
• d-matrix-ai / keyformer-llm
  ☆53Updated last year
• cat538 / SKVQ
  SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
  ☆19Updated 7 months ago
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆41Updated last week
• tsinghua-ideal / Twilight
  Adaptive Attention Sparsity with Hierarchical Top-p Pruning
  ☆17Updated 3 months ago
• NonvolatileMemory / flash_tree_attn
  ☆19Updated 4 months ago
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆37Updated 10 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆85Updated last year
• Infini-AI-Lab / Sirius
  Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…
  ☆21Updated 8 months ago
• Infini-AI-Lab / APE
  ☆25Updated 2 months ago
• FFY0 / AdaKV
  The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  ☆73Updated 3 months ago
• amazon-science / piperag
  PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)
  ☆19Updated 10 months ago
• sail-sg / LongSpec
  LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification
  ☆52Updated 2 months ago
• SqueezeAILab / SqueezedAttention
  SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference
  ☆46Updated 5 months ago
• NEO-MLSys25 / NEO
  NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
  ☆25Updated 2 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆100Updated 3 weeks ago
• OpenSparseLLMs / Linear-MoE
  ☆82Updated this week
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆36Updated 8 months ago
• microsoft / chunk-attention
  ☆74Updated 3 weeks ago
• Gaffey / ExCP
  Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".
  ☆47Updated 10 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆65Updated 2 months ago
• hdong920 / LESS
  ☆49Updated 11 months ago