Does X-VLA run on Bimanual SO-100/SO-101?
Scope: Fine-tuning on bimanual SO data is documented upstream (so101_bimanual action mode); on-robot inference on a bimanual SO is not documented by a primary source.
Capabilities
| Capability | State | Notes | Evidence |
|---|---|---|---|
| Train / fine-tune | works | ev-lerobot-xvla-bimanual-train, ev-lerobot-xvla-so101-bimanual-mode, ev-hub-zonglin-xvla-biso100 | |
| Real-robot inference | no verified evidence | — | |
| Simulation inference | no verified evidence | — | |
| Teleop + record | no verified evidence | — |
Evidence 3 sources; the cell shows the highest tier
- T1 · upstream documentedofficial-docssource 2026-08-03verified 2026-10-24 (1d ago)lerobot 0.6.1
LeRobot v0.6.1 X-VLA guide: 'Training on Bimanual Robot' example fine-tunes lerobot/xvla-base on a bimanual SO-100 dataset with --policy.action_mode=so101_bimanual.
“--dataset.repo_id=<USER>/bimanual-so100-handover-cube \”
https://github.com/huggingface/lerobot/blob/v0.6.1/docs/source/xvla.mdx - T1 · upstream documentedofficial-docssource 2026-08-03verified 2026-10-24 (1d ago)lerobot 0.6.1
LeRobot v0.6.1 X-VLA ships a dedicated so101_bimanual action mode (12-D real action = 2x(5 joints + gripper), padded to the 20-D model action).
“The `so101_bimanual` action mode handles the mismatch between model output (20D) and real robot control (12D):”
https://github.com/huggingface/lerobot/blob/v0.6.1/docs/source/xvla.mdx - T3 · community reportedhub-checkpointsource 2025-12-12verified 2026-10-24 (1d ago)
config.json type=xvla; train_config.json dataset.repo_id=zonglin11/lerobot_bi_so100_pickup_lego, whose meta/info.json robot_type=bi_so100_follower (12 episodes).
https://huggingface.co/zonglin11/lerobot_bi_so100_pickup_lego
X-VLA inference speed by hardware robot-independent · inference cost only
| Compute | Runtime | Precision | Cams | p50 / p95 ms | Inference | Platform | Source |
|---|---|---|---|---|---|---|---|
| Jetson Orin Nano 8GB (Super) | TensorRT | fp16 | 3 @640x480 | 342.59 / 343.47 | 2.92 Hz | jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10conditionsboard: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations resized by the exported policy to 224x224; 10 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 3.04 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. | T3 · community reported |
| Jetson Orin Nano 8GB (Super) | ONNX (split) | fp16 | 3 | 391.55 / 407.33 | 2.55 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · tensorrt 10.16.2 (system, via ONNX Runtime TensorRT EP)conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 · onnxruntime-gpu: 1.24 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Configured EP priority 12 graphs TensorRT. System RAM 5395 MB in use. | T3 · community reported |
| Jetson Orin Nano 8GB (Super) | PyTorch eager | fp32 | 3 | 2313.5 / 2320.89 | 0.43 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · lerobot 0.6.1conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Stock LeRobot X-VLA policy in PyTorch FP32 (LeRobot 0.6.1 env). At 30 Hz control the 30-step chunk is overrun (author's control-rate fit). System RAM 5450 MB in use. | T3 · community reported |
Embed this cell
Badge for READMEs and model cards. It always shows the current state.
[](https://caniembody.pages.dev/compat/bi-so/xvla)<iframe src="https://caniembody.pages.dev/embed/bi-so/xvla" width="380" height="132" style="border:0" title="X-VLA on Bimanual SO-100/SO-101 | CanIEmbody"></iframe>History
- 2026-10-25 fecccd1 Initial release: robot policy compatibility matrix · Danilo Znamerovszkij