Alternatives and similar repositories for PSAttention

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

• FFY0 / AdaKV
  The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  ☆87Updated last month
• NJUNLP / MCSD
  Multi-Candidate Speculative Decoding
  ☆36Updated last year
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆44Updated this week
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆199Updated 5 months ago
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆30Updated 5 months ago
• zcli-charlie / Awesome-KV-Cache
  ☆76Updated 9 months ago
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆36Updated 3 weeks ago
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆59Updated last year
• FasterDecoding / SnapKV
  ☆268Updated 3 weeks ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆103Updated 4 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆123Updated 8 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆109Updated 4 months ago
• microsoft / RetrievalAttention
  Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
  ☆71Updated this week
• Jikai0Wang / OPT-Tree
  ☆25Updated 2 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆102Updated 3 months ago
• UCSB-NLP-Chang / KVLink
  ☆20Updated 3 months ago
• microsoft / chunk-attention
  ☆78Updated 3 months ago
• tsinghua-ideal / Twilight
  Adaptive Attention Sparsity with Hierarchical Top-p Pruning
  ☆19Updated 5 months ago
• yangyifei729 / KVSharer
  Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''
  ☆27Updated 9 months ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆48Updated 9 months ago
• d-matrix-ai / keyformer-llm
  ☆54Updated last year
• Jingyu6 / speculative_prefill
  ☆37Updated 2 months ago
• YaoJiayi / CacheBlend
  ☆125Updated 3 weeks ago
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆141Updated last week
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]
  ☆43Updated 3 weeks ago
• mutonix / pyramidinfer
  ☆43Updated 8 months ago
• 66RING / LongShortTokenDecoding
  Long short token decoding speed up 4x for long context LLM. A hundred lines of core code. Open source for learning.
  ☆8Updated last year
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆51Updated 9 months ago
• SuDIS-ZJU / llm-inference-all-in-one
  ☆13Updated 5 months ago
• Dominic789654 / LongGenBench
  Source code for the paper "LongGenBench: Long-context Generation Benchmark"
  ☆22Updated 10 months ago