FlashRT

Popular repositories Loading

1. FlashRT FlashRT Public

   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.…

   C++ 585 82

2. FlashRT-HF-kernels FlashRT-HF-kernels Public

   FlashRT-HF-kernels contains standalone FlashRT CUDA/CUTLASS kernels prepared for the Hugging Face kernels community, focusing on small-batch, low-latency inference paths for LLM, VLA, and physical …

   Python 23 7

3. kernels kernels Public

   Forked from huggingface/kernels

   Build compute kernels and load them from the Hub.

   Python 2

4. FlashRT-Structures FlashRT-Structures Public

   Attach FlashRT's verified acceleration structures to an unmodified PyTorch host (lerobot, Isaac-GR00T, openpi, transformers, diffusers, vLLM, SGLang) with no fork and no edit to the host. Kernels a…

   Python 2 2

5. FlashRT-llama.cpp FlashRT-llama.cpp Public

   The FlashRT layer for llama.cpp hosts: fused-structure windows over ggml-cuda driven by FlashRT kernels. Mounted by a host at ggml/src/ggml-cuda/flashrt; vendors the FlashRT kernels it needs, carri…

   Cuda 2

6. FlashRT-assets FlashRT-assets Public

   FlashRT-assets

   1