FLUX 3 Action DROID on H100
Optimized TensorRT runtime for the FLUX 3 Action DROID policy on NVIDIA H100, in two precisions: fp8 and bf16.
Requirements
- NVIDIA H100 80GB HBM3 (compute capability 9.0), TensorRT 11.3.0.99, CUDA 12.9, PyTorch with CUDA.
Test
python run.py --precision bf16 --inputs example/bf16/synthetic-inputs.safetensors --reference example/bf16/synthetic-reference.safetensors
python verify.py
Prepare real inputs from Black Forest Labs' released FLUX 3 Action DROID policy and checkpoint (FLUX Kommunity License). A synthetic example is included so the runtime can be tested without that download.
Licence
FLUX Kommunity License, non-commercial. See LICENSE.md and NOTICE.
- Downloads last month
- -