Alternatives and similar repositories for Twilight

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

• sspec-project / SparseSpec
  Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
  ☆82Updated last month
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆109Updated 10 months ago
• pku-liang / ArkVale
  ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)
  ☆52Updated last year
• flashinfer-ai / flashinfer-bench
  Building the Virtuous Cycle for AI-driven LLM Systems
  ☆140Updated this week
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆52Updated 5 months ago
• d-matrix-ai / keyformer-llm
  Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning
  ☆59Updated last year
• FFY0 / AdaKV
  The Official Implementation of Ada-KV [NeurIPS 2025]
  ☆125Updated 2 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆161Updated 3 months ago
• cat538 / SKVQ
  [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
  ☆25Updated last year
• xinhao-luo / ClusterFusion
  [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
  ☆66Updated last month
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆368Updated 6 months ago
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆153Updated 11 months ago
• OpenBitSys / BitDecoding
  [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆79Updated last month
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆67Updated last year
• lemyx / tilelang-dsa
  DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang
  ☆43Updated 2 months ago
• mit-han-lab / fastrl
  [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
  ☆130Updated last month
• mit-han-lab / flash-moba
  ☆220Updated 2 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆97Updated last month
• zhuzilin / flash-attention-with-sink
  ☆38Updated 5 months ago
• microsoft / RetrievalAttention
  Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
  ☆119Updated last month
• osayamenja / FlashMoE
  Distributed MoE in a Single Kernel [NeurIPS '25]
  ☆188Updated this week
• sjtu-zhao-lab / ClusterKV
  ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression (DAC'25)
  ☆22Updated 4 months ago
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆187Updated 4 months ago
• infinigence / HamiltonAttention
  ☆41Updated 3 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆148Updated last month
• LiuXiaoxuanPKU / OSD
  ☆64Updated last year
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆61Updated 10 months ago
• LoongServe / LoongServe
  ☆130Updated last year
• ruipeterpan / marconi
  Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]
  ☆49Updated 10 months ago
• meta-pytorch / KernelAgent
  Autonomous GPU Kernel Generation via Deep Agents
  ☆223Updated this week