kvcache-ai / MooncakeLinks
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
☆3,436Updated this week
Alternatives and similar repositories for Mooncake
Users that are interested in Mooncake are comparing it to the libraries listed below
Sorting:
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,807Updated 3 months ago
- FlashInfer: Kernel Library for LLM Serving☆3,211Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,450Updated this week
- Expert Parallelism Load Balancer☆1,209Updated 2 months ago
- My learning notes/codes for ML SYS.☆2,498Updated this week
- Community maintained hardware plugin for vLLM on Ascend☆773Updated this week
- Nano vLLM☆1,659Updated this week
- Analyze computation-communication overlap in V3/R1.☆1,059Updated 3 months ago
- Redis for LLMs☆1,560Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆791Updated 2 weeks ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆978Updated 3 weeks ago
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,144Updated this week
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆1,173Updated this week
- DeepEP: an efficient expert-parallel communication library☆7,911Updated this week
- Distributed RL System for LLM Reasoning☆1,774Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,824Updated last month
- 📚A curated list of Awesome LLM Inference Papers with Codes.☆4,124Updated this week
- A self-learning tutorail for CUDA High Performance Programing.☆641Updated 2 months ago
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,151Updated last week
- A PyTorch Native LLM Training Framework☆819Updated 5 months ago
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,517Updated last week
- vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization☆1,350Updated this week
- SGLang is a fast serving framework for large language models and vision language models.☆15,276Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,317Updated this week
- Fast, Flexible and Portable Structured Generation☆1,008Updated last week
- 一种任务级GPU算力分时调度的高性能深度学习训练平台☆651Updated last year
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,798Updated 2 months ago
- FlashMLA: Efficient MLA decoding kernels☆11,607Updated last month
- DLRover: An Automatic Distributed Deep Learning System☆1,482Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆614Updated 2 months ago