Skip to content

@kvcache-ai kvcache.ai

Change the repository type filter

All

    Repositories list

    15 repositories

    • Mooncake

      Public
      Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
      reinforcement-learninginferencerdma
      reinforcement-learninginferencerdmadisaggregationllmvllmsglangkvcachetrt-llmtokenspeed
      C++
      •
      Apache License 2.0
      •865•5.6k•302•206•Updated Jun 22, 2026Jun 22, 2026

    • ktransformers

      Public
      A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
      Python
      •
      Apache License 2.0
      •1.3k•17k•445•8•Updated Jun 21, 2026Jun 21, 2026

    • sglang

      Public
      SGLang is a fast serving framework for large language models and vision language models.
      Python
      •
      Apache License 2.0
      •6.6k•11•0•13•Updated Jun 21, 2026Jun 21, 2026

    • kvcache-blog

      Public
      JavaScript
      •
      MIT License
      •9•12•0•1•Updated Jun 20, 2026Jun 20, 2026

    • Model-Optimizer

      Public
      A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models …
      Python
      •
      Apache License 2.0
      •453•0•0•0•Updated Jun 17, 2026Jun 17, 2026

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •18k•15•0•1•Updated Jun 16, 2026Jun 16, 2026

    • accelerate

      Public
      🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-…
      Python
      •
      Apache License 2.0
      •1.4k•1•0•1•Updated May 9, 2026May 9, 2026

    • transformers

      Public
      🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference an…
      Python
      •
      Apache License 2.0
      •34k•0•0•1•Updated May 9, 2026May 9, 2026

    • sglang_awq

      Public
      SGLang is a fast serving framework for large language models and vision language models.
      Python
      •
      Apache License 2.0
      •6.6k•2•0•0•Updated Apr 22, 2026Apr 22, 2026

    • evalscope

      Public
      A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
      Python
      •
      Apache License 2.0
      •404•0•0•0•Updated Apr 13, 2026Apr 13, 2026

    • DeepEP_fault_tolerance

      Public
      DeepEP: an efficient expert-parallel communication library that supports fault tolerance
      Cuda
      •
      MIT License
      •1.3k•3•0•0•Updated Jan 5, 2026Jan 5, 2026

    • gpustack

      Public
      GPU cluster manager for optimized AI model deployment
      Python
      •
      Apache License 2.0
      •549•0•0•0•Updated Dec 7, 2025Dec 7, 2025

    • TrEnv-X

      Public
      Go
      •
      Apache License 2.0
      •8•87•0•0•Updated Sep 15, 2025Sep 15, 2025

    • sglang-npu

      Public
      SGLang is a fast serving framework for large language models and vision language models.
      Python
      •
      Apache License 2.0
      •6.6k•0•0•0•Updated Aug 12, 2025Aug 12, 2025

    • custom_flashinfer

      Public
      FlashInfer: Kernel Library for LLM Serving
      Cuda
      •
      Apache License 2.0
      •1.1k•7•0•0•Updated Jul 24, 2025Jul 24, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.