address review

docs/source/hil_data_collection.mdx

@@ -68,12 +68,12 @@ The `lerobot-rollout --strategy.type=dagger` mode requires **teleoperators with
 
 ## Script
 
-Use `lerobot-rollout` with `--strategy.type=dagger` for HIL data collection. Toggle RTC with `--rtc.enabled=true`:
+Use `lerobot-rollout` with `--strategy.type=dagger` for HIL data collection. Select the inference backend with `--inference.type=sync|rtc`:
 
-| Mode                     | Flag                 | Models                |
-| ------------------------ | -------------------- | --------------------- |
-| Standard (default)       | _(no flag needed)_   | ACT, Diffusion Policy |
-| Real-Time Chunking (RTC) | `--rtc.enabled=true` | Pi0, Pi0.5, SmolVLA   |
+| Mode                     | Flag                   | Models                |
+| ------------------------ | ---------------------- | --------------------- |
+| Standard (default)       | _(no flag needed)_     | ACT, Diffusion Policy |
+| Real-Time Chunking (RTC) | `--inference.type=rtc` | Pi0, Pi0.5, SmolVLA   |
 
 ---
 
@@ -122,10 +122,10 @@ For models with high inference latency, enable RTC for smooth execution:
 
 ```bash
 lerobot-rollout --strategy.type=dagger \
-    --rtc.enabled=true \
-    --rtc.execution_horizon=20 \
-    --rtc.max_guidance_weight=5.0 \
-    --rtc.prefix_attention_schedule=LINEAR \
+    --inference.type=rtc \
+    --inference.rtc.execution_horizon=20 \
+    --inference.rtc.max_guidance_weight=5.0 \
+    --inference.rtc.prefix_attention_schedule=LINEAR \
     --robot.type=bi_openarm_follower \
     --robot.left_arm_config.port=can1 \
     --robot.left_arm_config.side=left \

docs/source/il_robots.mdx

@@ -542,4 +542,4 @@ The `--strategy.type` flag selects the execution mode:
 - `highlight`: Ring buffer recording with keystroke save (useful for capturing interesting events)
 - `dagger`: Human-in-the-loop data collection (see [HIL Data Collection](./hil_data_collection))
 
-All strategies support `--rtc.enabled=true` for smooth execution with slow VLA models (Pi0, Pi0.5, SmolVLA).
+All strategies support `--inference.type=rtc` for smooth execution with slow VLA models (Pi0, Pi0.5, SmolVLA).

docs/source/rtc.mdx

@@ -34,7 +34,7 @@ pip install -e ".[smolvla]"
 
 ### Using RTC with Pi0
 
-You can use `lerobot-rollout --strategy.type=base --rtc.enabled=true` for RTC deployment on real robots.
+You can use `lerobot-rollout --strategy.type=base --inference.type=rtc` for RTC deployment on real robots.
 The snippet below provides a simplified pseudo-example of how RTC operates with Pi0 in your pipeline:
 
 ```python
@@ -140,9 +140,9 @@ The script generates a visualization of the denoising process, comparing standar
 lerobot-rollout \
     --strategy.type=base \
     --policy.path=${HF_USERNAME}/policy_repo_id \
-    --rtc.enabled=true \
-    --rtc.execution_horizon=10 \
-    --rtc.max_guidance_weight=10.0 \
+    --inference.type=rtc \
+    --inference.rtc.execution_horizon=10 \
+    --inference.rtc.max_guidance_weight=10.0 \
     --robot.type=so100_follower \
     --robot.port=/dev/tty.usbmodem58FA0834591 \
     --robot.cameras="{ gripper: {type: opencv, index_or_path: 1, width: 640, height: 480, fps: 30}, front: {type: opencv, index_or_path: 0, width: 640, height: 480, fps: 30}}" \

docs/source/unitree_g1.mdx

@@ -284,7 +284,7 @@ python examples/rtc/eval_with_real_robot.py \
   --task="task_description" \
   --duration=1000 \
   --fps=30 \
-  --rtc.enabled=true
+  --inference.type=rtc
 ```
 
 ---