Add simple client CPU-only dry run#952
Draft
Travor278 wants to merge 1 commit into
Draft
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds a CPU-only dry-run policy server for
examples/simple_clientand an optional--show-action-chunkclient flag. This lets users validate the websocket path, fake observation payloads, and returnedactionschunk shape before downloading checkpoints, using a GPU, or connecting robot hardware.The existing simple client defaults are unchanged. The fake server is an example-only utility and does not affect model loading or real policy serving.
Related Issue
Related to #828 and #826.
Motivation and Context
Several users are trying to understand the remote policy server/client workflow, including which config/checkpoint pair to serve and what a basic action chunk response looks like. A lightweight dry run makes it easier to separate websocket/client setup issues from model checkpoint, GPU, or robot deployment issues.
How Has This Been / Can This Be Tested?
Tested locally on Windows with Anaconda
py311/ Python 3.11.15 using the simple-client dependencies.Smoke-tested the dry-run websocket path:
The client printed
actions shape=(4, 3)and timing stats for the fake server response.Checklist
policy:checkpointserver command.