Alternatives and similar repositories for MegaScale-Infer-Prototyp

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

• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆265Updated 2 months ago
• stepfun-ai / StepMesh
  ☆329Updated last month
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆135Updated last year
• hao-ai-lab / MuxServe
  ☆79Updated 2 months ago
• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆82Updated 9 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆90Updated 9 months ago
• UChi-JCL / CacheGen
  ☆142Updated last year
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆203Updated last year
• LoongServe / LoongServe
  ☆125Updated last year
• microsoft / sarathi-serve
  A low-latency & high-throughput serving engine for LLMs
  ☆456Updated 2 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆137Updated last month
• microsoft / tokenweave
  Efficient Compute-Communication Overlap for Distributed LLM Inference
  ☆66Updated last month
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆158Updated 2 months ago
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆66Updated last year
• tyler-griggs / melange-release
  ☆48Updated last year
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆172Updated last year
• nex-agi / NexVenusCL
  Nex Venus Communication Library
  ☆66Updated last month
• Hsword / SpotServe
  SpotServe: Serving Generative Large Language Models on Preemptible Instances
  ☆133Updated last year
• interestingLSY / swiftLLM
  A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …
  ☆297Updated 6 months ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆331Updated last year
• YaoJiayi / CacheBlend
  ☆156Updated 5 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆93Updated 2 years ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆196Updated 2 months ago
• microsoft / nnscaler
  nnScaler: Compiling DNN models for Parallel Training
  ☆120Updated 2 months ago
• Dao-AILab / sonic-moe
  Accelerating MoE with IO and Tile-aware Optimizations
  ☆351Updated this week
• meta-pytorch / torchcomms
  torchcomms: a modern PyTorch communications API
  ☆309Updated this week
• zcli-charlie / Awesome-KV-Cache
  ☆84Updated last year
• CalvinXKY / mfu_calculation
  A simple calculation for LLM MFU.
  ☆50Updated 3 months ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆64Updated 3 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆357Updated 5 months ago