FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B
☆586Sep 19, 2026Updated this week
Alternatives and similar repositories for FlashRT
Users that are interested in FlashRT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆46Sep 5, 2026Updated 2 weeks ago
- ☆23Updated this week
- Running VLA at 30Hz frame rate and 480Hz trajectory frequency☆616Feb 10, 2026Updated 7 months ago
- ☆109May 27, 2026Updated 3 months ago
- ☆156Mar 31, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- High-performance, light-weight C++ LLM and VLM Inference Software for Physical AI☆565Sep 3, 2026Updated 2 weeks ago
- A Pragmatic VLA Foundation Model☆1,831Jun 11, 2026Updated 3 months ago
- High-performance GPU kernels written in TIRx.☆104Updated this week
- A performance analysis tool for VLA models☆91Feb 26, 2026Updated 6 months ago
- RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI☆5,333Updated this week
- Real-Time VLAs via Future-state-aware Asynchronous Inference.☆501Apr 22, 2026Updated 5 months ago
- Galaxea's open-source VLA repository☆795Aug 13, 2026Updated last month
- A lightweight toolkit for quantitatively scoring LeRobot episodes.☆75Mar 13, 2026Updated 6 months ago
- ☆28Aug 25, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Sep 11, 2026Updated last week
- ☆23May 11, 2026Updated 4 months ago
- An Optimizer for Nvidia Compilers.☆136Sep 15, 2026Updated last week
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing☆3,707Updated this week
- ☆32Jul 2, 2025Updated last year
- LeflexiTac: Giving robots a sense of touch.☆117May 6, 2026Updated 4 months ago
- ☆13,931Aug 24, 2026Updated 3 weeks ago
- An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch…☆143Updated this week
- ☆459Aug 26, 2026Updated 3 weeks ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- mKernel: fast multi-node, multi-GPU fused kernels☆280Updated this week
- An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.☆704Updated this week
- Official Repository for MolmoAct2☆766Aug 23, 2026Updated 3 weeks ago
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆233Updated this week
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆22Nov 28, 2025Updated 9 months ago
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,060Sep 14, 2026Updated last week
- ☆119Updated this week
- Official repo for "StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation"☆31Jun 29, 2026Updated 2 months ago
- ☆232Aug 26, 2026Updated 3 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Some funny cute/cuteDSL code snippets☆35Mar 2, 2026Updated 6 months ago
- Official code of RDT 2☆805Feb 7, 2026Updated 7 months ago
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆548Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,472Updated this week
- FastCrest Tether: the OSS edge-to-cloud AI deploy CLI. Optimize, verify, deploy across Jetson, RTX, Apple Silicon, AMD. Hybrid edge-cloud…☆84Updated this week
- Building General-Purpose Robots Based on Embodied Foundation Model☆1,274Updated this week
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 8 months ago