kvcache-ai / MooncakeLinks
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
☆3,592Updated this week
Alternatives and similar repositories for Mooncake
Users that are interested in Mooncake are comparing it to the libraries listed below
Sorting:
- FlashInfer: Kernel Library for LLM Serving☆3,380Updated this week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,828Updated 4 months ago
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,159Updated this week
- My learning notes/codes for ML SYS.☆2,928Updated this week
- Community maintained hardware plugin for vLLM on Ascend☆881Updated this week
- Expert Parallelism Load Balancer☆1,237Updated 3 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,012Updated this week
- DLRover: An Automatic Distributed Deep Learning System☆1,502Updated last week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,525Updated 2 weeks ago
- Analyze computation-communication overlap in V3/R1.☆1,077Updated 3 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,388Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆812Updated last month
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,239Updated this week
- Distributed RL System for LLM Reasoning☆2,018Updated this week
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,227Updated last week
- DeepEP: an efficient expert-parallel communication library☆8,282Updated this week
- A PyTorch Native LLM Training Framework☆831Updated last week
- A Datacenter Scale Distributed Inference Serving Framework☆4,496Updated this week
- Supercharge Your LLM with the Fastest KV Cache Layer☆3,080Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,705Updated last week
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆1,329Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,835Updated 3 months ago
- vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization☆1,498Updated this 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☆671Updated last year
- SGLang is a fast serving framework for large language models and vision language models.☆16,097Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,872Updated 2 months ago
- ☆463Updated this week
- A self-learning tutorail for CUDA High Performance Programing.☆680Updated 2 weeks ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,112Updated this week
- LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.☆798Updated this week