Alternatives and similar repositories for llm_kvcache_sparsity

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

• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆128Updated 2 weeks ago
• d-matrix-ai / keyformer-llm
  ☆58Updated last year
• FFY0 / AdaKV
  The Official Implementation of Ada-KV [NeurIPS 2025]
  ☆110Updated last month
• zcli-charlie / Awesome-KV-Cache
  ☆80Updated last year
• InternLM / Awesome-LLM-Training-System
  ☆43Updated last year
• madsys-dev / deepseekv2-profile
  ☆151Updated 8 months ago
• microsoft / chunk-attention
  ☆81Updated 6 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆346Updated 4 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆106Updated 7 months ago
• ClubieDong / QAQ-KVCacheQuantization
  QAQ: Quality Adaptive Quantization for LLM KV Cache
  ☆54Updated last year
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆61Updated last year
• LoongServe / LoongServe
  ☆124Updated last year
• cat538 / SKVQ
  [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
  ☆24Updated last year
• TreeAI-Lab / Awesome-KV-Cache-Management
  This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding co…
  ☆237Updated 3 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆87Updated 5 months ago
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆63Updated last year
• DD-DuDa / BitDecoding
  [HPCA 2025] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆62Updated this week
• interestingLSY / swiftLLM
  A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …
  ☆286Updated 5 months ago
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆47Updated 4 months ago
• FasterDecoding / SnapKV
  ☆287Updated 4 months ago
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆66Updated last year
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆169Updated last year
• mdy666 / mdy_triton
  ☆148Updated 4 months ago
• NJUNLP / MCSD
  Multi-Candidate Speculative Decoding
  ☆36Updated last year
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆93Updated 2 years ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆222Updated 2 years ago
• thu-pacman / FasterMoE
  ☆87Updated 3 years ago
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆169Updated last month
• chenhongyu2048 / LLM-inference-optimization-paper
  Summary of some awesome work for optimizing LLM inference
  ☆135Updated 2 weeks ago
• MoE-Inf / awesome-moe-inference
  Curated collection of papers in MoE model inference
  ☆297Updated 3 weeks ago