admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-17 09:39:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(eval): implement docker runtime with HTTP policy inference server

Browse Source 
Add docker_runtime.py (host-side) and lerobot_eval_worker.py (container-side)
for --eval.runtime=docker. Policy loads once on the host GPU; Docker containers
run env-only workers that call back via HTTP for action chunks, maximising GPU
utilisation across parallel benchmark tasks.

- _InferenceServer: HTTP server wrapping predict_action_chunk with a single lock
- run_eval_in_docker: spawns instance_count containers, collects + merges per-task
  JSON, writes eval_info.json compatible with _aggregate_eval_from_per_task
- lerobot-eval-worker CLI: make_env → shard tasks → run episodes → write JSON
- EvalDockerConfig: add port field (default 50051)
- pyproject.toml: add lerobot-eval-worker entry point

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Pepijn
2026-03-20 22:35:59 -07:00
parent e80c9e6270
commit 3d5d8fa88a
4 changed files with 507 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pyproject.toml
+1
View File
@@ -247,6 +247,7 @@ lerobot-replay="lerobot.scripts.lerobot_replay:main"
lerobot-setup-motors="lerobot.scripts.lerobot_setup_motors:main"
lerobot-teleoperate="lerobot.scripts.lerobot_teleoperate:main"
lerobot-eval="lerobot.scripts.lerobot_eval:main"
lerobot-eval-worker="lerobot.scripts.lerobot_eval_worker:main"
lerobot-train="lerobot.scripts.lerobot_train:main"
lerobot-train-tokenizer="lerobot.scripts.lerobot_train_tokenizer:main"
lerobot-dataset-viz="lerobot.scripts.lerobot_dataset_viz:main"