Alternatives and similar repositories for dynamo

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

• LMCache / LMCache
  Supercharge Your LLM with the Fastest KV Cache Layer
  ☆3,716Updated this week
• flashinfer-ai / flashinfer
  FlashInfer: Kernel Library for LLM Serving
  ☆3,448Updated this week
• vllm-project / production-stack
  vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
  ☆1,558Updated last week
• vllm-project / aibrix
  Cost-efficient and pluggable Infrastructure components for GenAI inference
  ☆3,955Updated this week
• kvcache-ai / Mooncake
  Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
  ☆3,665Updated this week
• deepseek-ai / open-infra-index
  Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
  ☆7,876Updated 2 months ago
• sgl-project / sglang
  SGLang is a fast serving framework for large language models and vision language models.
  ☆16,386Updated this week
• vllm-project / llm-compressor
  Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
  ☆1,690Updated last week
• deepseek-ai / DualPipe
  A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
  ☆2,835Updated 4 months ago
• deepseek-ai / EPLB
  Expert Parallelism Load Balancer
  ☆1,240Updated 4 months ago
• deepseek-ai / DeepGEMM
  DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
  ☆5,562Updated this week
• GeeeekExplorer / nano-vllm
  Nano vLLM
  ☆5,516Updated last month
• deepseek-ai / DeepEP
  DeepEP: an efficient expert-parallel communication library
  ☆8,316Updated last week
• mirage-project / mirage
  Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA
  ☆1,629Updated this week
• deepseek-ai / profile-data
  Analyze computation-communication overlap in V3/R1.
  ☆1,081Updated 4 months ago
• bytedance / flux
  A fast communication-overlapping library for tensor/expert parallelism on GPUs.
  ☆1,037Updated 2 weeks ago
• tile-ai / tilelang
  Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
  ☆1,472Updated this week
• deepseek-ai / 3FS
  A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
  ☆9,166Updated this week
• deepseek-ai / smallpond
  A lightweight data processing framework built on DuckDB and 3FS.
  ☆4,749Updated 4 months ago
• pytorch / ao
  PyTorch native quantization and sparsity for training and inference
  ☆2,219Updated this week
• ModelTC / LightLLM
  LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…
  ☆3,412Updated this week
• HazyResearch / ThunderKittens
  Tile primitives for speedy kernels
  ☆2,541Updated this week
• zhaochenyang20 / Awesome-ML-SYS-Tutorial
  My learning notes/codes for ML SYS.
  ☆3,080Updated last week
• linkedin / Liger-Kernel
  Efficient Triton Kernels for LLM Training
  ☆5,419Updated last week
• mit-han-lab / llm-awq
  [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
  ☆3,181Updated 2 weeks ago
• huggingface / picotron
  Minimalistic 4D-parallelism distributed training framework for education purpose
  ☆1,619Updated 3 weeks ago
• pytorch / torchtitan
  A PyTorch native platform for training generative AI models
  ☆4,125Updated this week
• mlc-ai / xgrammar
  Fast, Flexible and Portable Structured Generation
  ☆1,111Updated this week
• huggingface / nanotron
  Minimalistic large language model 3D-parallelism training
  ☆2,068Updated 3 weeks ago
• NVIDIA / TransformerEngine
  A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…
  ☆2,587Updated this week