Alternatives and similar repositories for MegaScale-Infer-Prototyp

Users that are interested in MegaScale-Infer-Prototyp are comparing it to the libraries listed below

• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆130Updated 11 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆125Updated last week
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆326Updated last year
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆169Updated last year
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆85Updated last year
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆151Updated 3 weeks ago
• FasterDecoding / SnapKV
  ☆286Updated 3 months ago
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆144Updated 9 months ago
• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆80Updated 8 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆344Updated 3 months ago
• pan-x-c / EE-LLM
  EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).
  ☆69Updated last year
• hao-ai-lab / Dynasor
  [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
  ☆201Updated 5 months ago
• tyler-griggs / melange-release
  ☆48Updated last year
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆240Updated 11 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆111Updated 7 months ago
• microsoft / sarathi-serve
  A low-latency & high-throughput serving engine for LLMs
  ☆436Updated 3 weeks ago
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆254Updated 3 weeks ago
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆144Updated 8 months ago
• shreyansh26 / Speculative-Sampling
  Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind
  ☆105Updated last year
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆189Updated last year
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆168Updated last month
• InternLM / turbomind
  ☆97Updated 7 months ago
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆145Updated last year
• LiuXiaoxuanPKU / OSD
  ☆60Updated 11 months ago
• hao-ai-lab / MuxServe
  ☆75Updated 3 weeks ago
• MDK8888 / vllmini
  A minimal implementation of vllm.
  ☆60Updated last year
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆106Updated 7 months ago
• FasterDecoding / TEAL
  ☆146Updated 8 months ago
• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆247Updated last month
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆145Updated 2 months ago