Alternatives and similar repositories for Mooncake

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

• flashinfer-ai / flashinfer
  FlashInfer: Kernel Library for LLM Serving
  ☆4,062Updated this week
• deepseek-ai / DualPipe
  A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
  ☆2,877Updated 8 months ago
• zhaochenyang20 / Awesome-ML-SYS-Tutorial
  My learning notes/codes for ML SYS.
  ☆4,136Updated this week
• deepseek-ai / EPLB
  Expert Parallelism Load Balancer
  ☆1,294Updated 7 months ago
• deepseek-ai / profile-data
  Analyze computation-communication overlap in V3/R1.
  ☆1,116Updated 7 months ago
• deepseek-ai / DeepGEMM
  DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
  ☆5,874Updated 3 weeks ago
• vllm-project / vllm-ascend
  Community maintained hardware plugin for vLLM on Ascend
  ☆1,338Updated this week
• tile-ai / tilelang
  Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
  ☆3,891Updated this week
• ModelTC / LightLLM
  LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…
  ☆3,717Updated this week
• thu-pacman / chitu
  High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
  ☆1,328Updated this week
• bytedance / flux
  A fast communication-overlapping library for tensor/expert parallelism on GPUs.
  ☆1,165Updated 2 months ago
• deepseek-ai / DeepEP
  DeepEP: an efficient expert-parallel communication library
  ☆8,712Updated last week
• alibaba / rtp-llm
  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
  ☆920Updated this week
• inclusionAI / AReaL
  Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
  ☆2,977Updated this week
• xlite-dev / Awesome-LLM-Inference
  📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
  ☆4,677Updated 2 months ago
• deepseek-ai / open-infra-index
  Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
  ☆7,931Updated 5 months ago
• ai-dynamo / dynamo
  A Datacenter Scale Distributed Inference Serving Framework
  ☆5,450Updated this week
• intelligent-machine-learning / dlrover
  DLRover: An Automatic Distributed Deep Learning System
  ☆1,584Updated last week
• volcengine / veScale
  A PyTorch Native LLM Training Framework
  ☆884Updated 2 months ago
• THUDM / slime
  slime is an LLM post-training framework for RL Scaling.
  ☆2,407Updated last week
• BBuf / how-to-optim-algorithm-in-cuda
  how to optimize some algorithm in cuda.
  ☆2,607Updated last week
• MoonshotAI / MoBA
  MoBA: Mixture of Block Attention for Long-Context LLMs
  ☆1,969Updated 7 months ago
• vllm-project / llm-compressor
  Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
  ☆2,215Updated this week
• vllm-project / production-stack
  vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
  ☆1,928Updated last week
• alibaba / Pai-Megatron-Patch
  The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
  ☆1,418Updated 2 weeks ago
• Tencent / KsanaLLM
  ☆511Updated 2 months ago
• deepseek-ai / FlashMLA
  FlashMLA: Efficient Multi-head Latent Attention Kernels
  ☆11,857Updated last month
• mlc-ai / xgrammar
  Fast, Flexible and Portable Structured Generation
  ☆1,355Updated last week
• InternLM / lmdeploy
  LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
  ☆7,231Updated last week
• modelscope / evalscope
  A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
  ☆1,937Updated this week