ac2sim - #46
Merged
Merged
Conversation
Add an isolated persistent MessagePack WebSocket endpoint for LingBot VLA v2 that accepts RoboTwin observations and returns absolute-position action chunks through the existing RobotWin profile. Document the standalone deployment flow and protocol dependency, and cover message encoding, observation mapping, reset handling, persistent connections, timing metadata, and CLI options. Verification: 18 focused LingBot VLA v2 tests passed; ruff check and git diff --check passed.
Advertise the raw action contract, propagate deterministic seeds and trace identifiers, validate mapped action chunks, and expose phase timings without changing shared TeleFuser APIs. Add a no-simulation WebSocket validator, focused unit coverage, dedicated client dependency, and the H100-to-RTX XPolicyLab deployment guide. Verification: ruff check; 46 LingBot-VLA v2 unit tests; 13 validator unit tests; CLI help; git diff --check.
Disable unsupported cuDNN SDPA plans only in the dedicated H100 RoboTwin policy process. Advertise and enforce the WebSocket request limit, resize oversized validation images, and document the module-based validator invocation and BF16 replay semantics. Verification: ruff check; ruff format --check; 141 LingBot VLA unit tests; real H100 direct WebSocket and XPolicyLab proxy smoke tests.
Add a bounded LingBot VLA v2 scheduler that serializes GPU inference while retaining only the newest pending request per session. Support sequence IDs, server-local request TTLs, structured stale-action responses, and explicit scheduling metadata without changing the shared service or model interfaces. Decouple WebSocket receive and response delivery so clients can submit observations while inference is active. Extend the no-simulation validator with sequential and overlap modes, and document the remaining RTX-side execution-buffer work. Verification: ruff check and format checks passed; focused scheduler/WebSocket tests passed (38); all LingBot VLA v2 CPU tests passed (151); real H100 sequential and three-request overlap validation passed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Motivation
Type of Change
Changes Made
Testing
pytest tests/)Test commands:
# Add the commands used to test your changes pytest tests/Checklist
ruff)pre-commit run --all-files)pytest tests/)[TYPE] Brief descriptionRelated Issues
Fixes #
Additional Notes
GPU Architecture Support
Performance Impact