Downloads · 30 days
0
Turbo-Pi0.5-1.1.2
liangsu9988/Turbo-Pi0.5-1.1.2
Turbo-Pi0.5-1.1.2 is a robotics model from liangsu9988. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for tensorrt. The card lists the license as apache-2.0.
19.2x faster Pi0.5 VLA model optimized for NVIDIA Jetson Thor
Access
Public
Updated Jan 30, 2026
Parameters
3.6B
16.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 90%
At a glance
- Task
- Robotics
- Library
- tensorrt
- License
- apache-2.0
- Access
- Public
- Created
- Jan 30, 2026
- Updated
- Jan 30, 2026
- SHA
- 294a58c3
Datasets
Model card
From the Hugging Face model README
Turbo-Pi0.5 v1.1.2
19.2x faster Pi0.5 VLA model optimized for NVIDIA Jetson Thor
Performance
| Metric | Original (JAX) | Turbo-Pi (TRT Pipelined) |
|---|---|---|
| Inference Speed | 1.4 Hz | 26.9 Hz |
| Latency | 714 ms | 37.2 ms |
| LIBERO Spatial | 98% | 98% |
| LIBERO 10 | 91% | 91% |
Key Optimizations
- KV Cache: Efficient denoising with 3.7x speedup
- TensorRT FP16: Hardware-accelerated inference
- Dual-stream Pipeline: +25% throughput with concurrent execution
- Reduced Steps: 10 → 3 denoising steps with <1% accuracy loss
Model Architecture
- Vision Encoder: SigLIP-SO400M (400M params)
- Language Model: Gemma 2B
- Action Expert: Gemma 300M with adaRMSNorm
Files
.
├── model.safetensors # PyTorch model weights (13.5 GB)
├── config.json # Model configuration
├── policy_preprocessor.json # Input normalization stats
├── policy_postprocessor.json # Output denormalization stats
└── tensorrt_engines/ # Pre-built TensorRT engines (Jetson Thor)
├── siglip_vision_encoder.engine (790 MB)
└── gemma_300m_expert_adarms_fp16.engine (818 MB)
Quick Start
Option 1: Python API
from openpi.inference import UnifiedPolicy
policy = UnifiedPolicy(
checkpoint_dir="~/.cache/openpi/checkpoints/pi05_libero",
backend="tensorrt_pipelined", # or "pytorch"
num_denoising_steps=3,
)
result = policy.infer({
"observation/image": image, # (224, 224, 3) uint8
"observation/wrist_image": wrist_img, # (224, 224, 3) uint8
"observation/state": state, # (8,) float32
"prompt": "pick up the black bowl",
})
actions = result["actions"] # (50, 7) action chunk
Option 2: Download
huggingface-cli download liangsu9988/Turbo-Pi0.5-1.1.2 \
--local-dir ~/.cache/openpi/checkpoints/pi05_libero
Hardware Requirements
- Recommended: NVIDIA Jetson Thor (JetPack 7.1+)
- Minimum: GPU with 8GB+ VRAM, CUDA 12.0+
- Memory: ~7.65 GB GPU memory usage
Benchmark Results
LIBERO Spatial (10 tasks x 10 trials)
| Task | Success |
|---|---|
| pick_up_black_bowl_between_plate_and_ramekin | 90% |
| pick_up_black_bowl_next_to_ramekin | 100% |
| pick_up_black_bowl_from_table_center | 100% |
| pick_up_black_bowl_on_cookie_box | 100% |
| pick_up_black_bowl_in_top_drawer | 100% |
| pick_up_black_bowl_on_ramekin | 100% |
| pick_up_black_bowl_next_to_cookie_box | 100% |
| pick_up_black_bowl_on_stove | 100% |
| pick_up_black_bowl_next_to_plate | 90% |
| pick_up_black_bowl_on_wooden_cabinet | 100% |
| Total | 98% |
LIBERO 10 (10 tasks x 10 trials)
| Task | Success |
|---|---|
| put_alphabet_soup_and_tomato_sauce_in_basket | 90% |
| put_cream_cheese_and_butter_in_basket | 100% |
| turn_on_stove_and_put_moka_pot | 80% |
| put_bowl_in_drawer_and_close | 100% |
| put_mugs_on_plates | 100% |
| pick_up_book_place_in_caddy | 100% |
| put_mug_on_plate_pudding_to_right | 90% |
| put_alphabet_soup_and_cream_cheese_in_basket | 100% |
| put_both_moka_pots_on_stove | 50% |
| put_mug_in_microwave_and_close | 100% |
| Total | 91% |
Version History
- v1.1.2 (2026-01-30): Fixed quantile normalization, LIBERO Spatial 98%, LIBERO 10 91%
- v1.1.0 (2026-01-29): Dual-stream pipelined TensorRT, 26.9 Hz
- v1.0.0 (2026-01-29): Initial release with KV Cache + TensorRT FP16
Links
- GitHub: LiangSu8899/TurboPi
- Base Model: Physical Intelligence Pi0
License
Apache License 2.0
Acknowledgments
Based on OpenPi by Physical Intelligence.
- Task
- Robotics
- Library
- tensorrt
- License
- apache-2.0
- Languages
- en
- Created
- Jan 30, 2026
- Updated
- Jan 30, 2026