PyPI page
Home page
License:
Apache-2.0
Summary:
FlashRT — realtime CUDA inference engine for small-batch, latency-sensitive AI workloads. Ships VLA frontends for Pi0, Pi0.5, Pi0-FAST, GROOT N1.6/N1.7.
Latest version:
0.2.0
Required dependencies:
numpy
|
pyyaml
Optional dependencies:
diffusers
|
einops
|
fastapi
|
flash-attn
|
flash-rt
|
flax
|
jax
|
jaxlib
|
ml-dtypes
|
nvidia-cublas
|
nvidia-cutlass-dsl
|
opencv-python
|
orbax-checkpoint
|
pillow
|
quack-kernels
|
safetensors
|
sageattention
|
scipy
|
sentencepiece
|
torch
|
tqdm
|
transformers
|
uvicorn
Downloads last day:
0
Downloads last week:
11
Downloads last month:
141
7-day smoothing