Alternatives and similar repositories for MagicDec

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

• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆103Updated last month
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆161Updated 10 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆73Updated 8 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆103Updated this week
• FasterDecoding / SnapKV
  ☆242Updated last year
• FasterDecoding / TEAL
  ☆129Updated 3 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆94Updated last month
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆308Updated 10 months ago
• RulinShao / LightSeq
  Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training
  ☆209Updated 8 months ago
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆127Updated 3 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆286Updated 5 months ago
• InternLM / turbomind
  ☆84Updated last month
• snowflakedb / ArcticInference
  ☆59Updated this week
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆69Updated 11 months ago
• d-matrix-ai / keyformer-llm
  ☆54Updated last year
• jy-yuan / KIVI
  [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
  ☆295Updated 3 months ago
• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆78Updated 2 months ago
• thu-pacman / FasterMoE
  ☆82Updated 3 years ago
• whyNLP / LCKV
  Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…
  ☆149Updated last month
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆109Updated 2 months ago
• FasterDecoding / REST
  REST: Retrieval-Based Speculative Decoding, NAACL 2024
  ☆201Updated 5 months ago
• SqueezeAILab / KVQuant
  [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  ☆352Updated 9 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆85Updated last year
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆55Updated 10 months ago
• microsoft / chunk-attention
  ☆75Updated last month
• ClubieDong / QAQ-KVCacheQuantization
  QAQ: Quality Adaptive Quantization for LLM KV Cache
  ☆49Updated last year
• stanford-futuredata / stk
  ☆104Updated 8 months ago
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆182Updated this week
• LiuXiaoxuanPKU / OSD
  ☆49Updated 5 months ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆45Updated 7 months ago