Add opencode_hf_sandbox.py: loop-owning training in remote HF sandboxes - #6565
Draft
sergiopaniego wants to merge 1 commit into
Draft
Add opencode_hf_sandbox.py: loop-owning training in remote HF sandboxes#6565sergiopaniego wants to merge 1 commit into
sergiopaniego wants to merge 1 commit into
Conversation
Sibling of opencode.py that runs each rollout in its own remote Hugging Face sandbox (HFSandboxBackend) to scale rollouts beyond a single node. Adds the script + its rows in example_overview.md and the openenv.md guide.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Adds
examples/scripts/openenv/opencode_hf_sandbox.py, a sibling ofopencode.pythat runs each loop-owning rollout in its own remote Hugging Face sandbox (HFSandboxBackend) instead of a local subprocess, so rollouts scale out beyond a single node.It reuses the same DeepCoder task, held-out verifier, reward and hooks as
opencode.py. The delta is where the rollout runs: a pre-baked remote sandbox image, and a two-URL topology (trainer to vLLM on localhost for NCCL weight-sync, remote sandboxes reach the same vLLM through a public URL). Also adds the example toexample_overview.mdand a note in theopenenv.mdguide.Draft, do-not-merge until OpenEnv PR huggingface/OpenEnv#1010 lands on main (it moves the sandbox layer to
openenv.core.sandbox, the import this example uses).AI writing disclosure
cc @AmineDiro