Organization card

README.md

@@ -10,19 +10,28 @@ pinned: false
 # ZenEdgeX
 
 **Proprio: exact inference for robot policies.** Proprio runs unmodified vision-language-action
-checkpoints (SmolVLA, pi0.5, GR00T N1.7) as recorded device graphs and verifies every action chunk
-bit for bit against the original model before serving it. If the actions are not identical, it refuses
-to deploy. Every run writes a Bitwise Certificate anyone can rerun.
+checkpoints faster and verifies every action chunk bit for bit against the original model before
+serving it. If the actions are not identical, it refuses to deploy. Every run writes a Bitwise
+Certificate anyone can rerun.
 
-Measured on an RTX 4090 with stock LeRobot checkpoints: SmolVLA 6.4x, pi0.5 2.7x, GR00T N1.7 2.7x,
-all ticks identical. For fleets: 16 SmolVLA robots per GPU at 12.5x per robot, every row identical
-to the robot alone.
+**New in 0.1.2: a drop-in for LeRobot async inference.** `proprio lerobot-server` takes the same
+flags as LeRobot's policy server; the robot client does not change. Against LeRobot's own server on
+an RTX 4090, same observations and seeds: SmolVLA 20/20 action chunks identical, about 330 ms to
+52 ms per chunk; pi0.5 20/20 identical. Guide: https://github.com/zenedgex/proprio-releases/blob/main/LEROBOT.md
 
+Model tick, eager against Proprio, all ticks identical (RTX 4090):
+
+| Policy | Eager | Proprio | |
+|---|---|---|---|
+| lerobot/smolvla_base | 232 ms | 37–40 ms | 5.9–6.3x |
+| lerobot/pi05_base (bf16) | 257 ms | 97 ms | 2.7x |
+| nvidia/GR00T-N1.7-3B | 170 ms | 64 ms | 2.7x |
+| openvla/openvla-7b | 209 ms | 145 ms (H100: 88 ms) | 1.4x (H100: 2.7x) |
+| 16 SmolVLA robots per tick | 240 ms | 19.3 ms per robot | 12.5x, every row identical to the robot alone |
+
+- Evaluation wheels, free, no key (Linux x86_64 and aarch64): https://github.com/zenedgex/proprio-releases
+- The certificates and server comparisons behind these numbers: the `proprio-certificates` dataset in this organization
 - Results: https://zenedgex.in/proprio/
-- Evaluation wheels, free, no key: https://github.com/zenedgex/proprio-releases
-- The certificates behind the numbers: the `proprio-certificates` dataset in this organization
-- Serving: openpi-compatible websocket server, LeRobot-shaped `RemotePolicy` client, Prometheus
-  metrics, and a proposed `robotics` Inference Providers task
+- Serving: LeRobot async-inference server, openpi-compatible websocket server, `proprio doctor` to check a machine first
 
-We are registering as an Inference Provider for the `robotics` task so any LeRobot policy page can be
-run exactly from the Hub. Contact: hello@zenedgex.in
+Patent pending. Contact: hello@zenedgex.in