Skip to content

@CentML CentML

Change the repository type filter

All

    Repositories list

    42 repositories

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •12k•0•0•11•Updated Jan 2, 2026Jan 2, 2026

    • dynamo

      Public
      A Datacenter Scale Distributed Inference Serving Framework
      Rust
      •
      Other
      •761•0•0•0•Updated Dec 25, 2025Dec 25, 2025

    • mlperf-inference

      Public
      Reference implementations of MLPerf™ inference benchmarks
      Python
      •
      Apache License 2.0
      •600•0•0•7•Updated Dec 24, 2025Dec 24, 2025

    • platform_api_python_client

      Public
      Python
      •0•0•0•3•Updated Dec 19, 2025Dec 19, 2025

    • pydantic-typer

      Public
      Typer extension to enable pydantic support
      Python
      •
      MIT License
      •3•0•0•0•Updated Dec 18, 2025Dec 18, 2025

    • openai-python

      Public
      The official Python library for the OpenAI API
      Python
      •
      Apache License 2.0
      •4.5k•0•0•0•Updated Dec 9, 2025Dec 9, 2025

    • codex

      Public
      A comprehensive collection of integration examples for CentML. This repository serves as a resource hub for developers looking to seamlessly incorporate CentML's capabilities into their applications. Explore a variety of use cases and implementations to accelerate your integration process.
      Python
      •
      Apache License 2.0
      •1•5•0•8•Updated Dec 2, 2025Dec 2, 2025

    • centml-python-client

      Public
      Python
      •
      Apache License 2.0
      •1•1•9•1•Updated Nov 26, 2025Nov 26, 2025

    • spiffe-jwt

      Public
      Go
      •
      Apache License 2.0
      •1•0•0•1•Updated Nov 20, 2025Nov 20, 2025

    • ecr-anywhere

      Public
      Pull from private ECR repos... anywhere
      Go
      •
      Apache License 2.0
      •1•1•1•0•Updated Oct 27, 2025Oct 27, 2025

    • lorafusion

      Public
      LoRAFusion: Efficient LoRA Fine-Tuning for LLMs
      Python
      •2•21•1•1•Updated Sep 23, 2025Sep 23, 2025

    • flexible-inference-bench

      Public
      A modular, extensible LLM inference benchmarking framework that supports multiple benchmarking frameworks and paradigms.
      Python
      •
      Apache License 2.0
      •1•12•9•0•Updated Aug 27, 2025Aug 27, 2025

    • Mist

      Public
      [EuroSys'25] Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization
      Python
      •
      Apache License 2.0
      •5•21•0•2•Updated Aug 6, 2025Aug 6, 2025

    • centml_platform_docs

      Public
      MDX
      •0•0•2•0•Updated Jul 24, 2025Jul 24, 2025

    • adk-python

      Public
      An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
      Python
      •
      Apache License 2.0
      •2.7k•0•0•0•Updated Jun 5, 2025Jun 5, 2025

    • cloudflare-operator

      Public
      A Kubernetes Operator to create and manage Cloudflare Tunnels and DNS records for (HTTP/TCP/UDP*) Service Resources
      Go
      •
      Apache License 2.0
      •59•0•0•0•Updated May 3, 2025May 3, 2025

    • aisuite

      Public
      Simple, unified interface to multiple Generative AI providers
      Python
      •
      MIT License
      •1.4k•0•0•8•Updated Apr 29, 2025Apr 29, 2025

    • Sylva

      Public
      Boost fine-tuning performance with sparse embedded adapters and hierarchical approximate second-order information.
      Python
      •
      Apache License 2.0
      •0•2•0•2•Updated Apr 29, 2025Apr 29, 2025

    • simple-sidecar

      Public
      A simple configurable kubernetes sidecar injector.
      Go
      •
      Apache License 2.0
      •1•0•0•0•Updated Apr 17, 2025Apr 17, 2025

    • paper-of-the

      Public
      An Agent that reviews the papers published on a given day and picks the one most aligned with our mission.
      TypeScript
      •
      Apache License 2.0
      •1•0•0•0•Updated Mar 14, 2025Mar 14, 2025

    • ai-benchmarks

      Public
      Benchmarking suite for popular AI APIs
      Python
      •
      MIT License
      •16•0•0•3•Updated Feb 12, 2025Feb 12, 2025

    • DeepView.Profile

      Public
      🏙 Interactive performance profiling and debugging tool for PyTorch neural networks.
      machine-learningdeep-neural-networksdeep-learningneural-network
      Python
      •
      Apache License 2.0
      •11•64•0•0•Updated Jan 21, 2025Jan 21, 2025

    • llama-stack

      Public
      Composable building blocks to build Llama Apps
      Python
      •
      MIT License
      •1.2k•0•0•0•Updated Jan 2, 2025Jan 2, 2025

    • DeepView.Predict

      Public
      🔮 Execution time predictions for deep neural network training iterations across different GPUs.
      Python
      •
      Apache License 2.0
      •3•14•3•0•Updated Dec 16, 2024Dec 16, 2024

    • DeepView.Explore

      Public
      🛠 VSCode plugin that provides visual interface for CentML Tools
      TypeScript
      •2•15•2•0•Updated Dec 5, 2024Dec 5, 2024

    • platform_docs

      Public archive
      CentML Platform Documentation
      MDX
      •11•0•0•0•Updated Nov 5, 2024Nov 5, 2024

    • FastChat

      Public
      An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
      Python
      •
      Apache License 2.0
      •4.8k•0•0•0•Updated Sep 17, 2024Sep 17, 2024

    • training-operator

      Public
      Distributed ML Training and Fine-Tuning on Kubernetes
      Go
      •
      Apache License 2.0
      •859•0•0•1•Updated Aug 22, 2024Aug 22, 2024

    • llm-inference-bench

      Public
      Lightweight and extensible LLM Inference serving benchmark tool written in Rust.
      benchmarkingllm-servingllm-inference
      Rust
      •0•4•0•0•Updated Apr 4, 2024Apr 4, 2024

    • examples

      Public
      A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •9.8k•0•0•0•Updated Feb 28, 2024Feb 28, 2024