[DYNAMO] wire TITO client to Dynamo renderer transport#2446
Draft
AmeenP wants to merge 1 commit into
Draft
Conversation
cfe5428 to
4a2503d
Compare
9cad934 to
360f0c1
Compare
3f89cf5 to
058755e
Compare
1c53674 to
0448473
Compare
0448473 to
ff77174
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Ports the missing prime-rl client-side TITO wiring from Biswa's tested branches on top of #2420 (
feat/dynamo-renderer-transport-config). The shared renderer/verifiers pins andreturn_token_idscleanup now live in #2420, so this PR only carries the TITO-specific follow-up.openai_chat_completions_tokenas token-aware forclient.backend = "dynamo"renderer_transport="dynamo"for both renderer-mode and TITO clients when using DynamoBiswa Compatibility Notes
Included from Biswa's
rl-sdk-2where it matches the current Dynamo contract:return_token_idsdefault in [DYNAMO] pass renderer transport to verifiers #2420Not included yet:
compute_teacher_logprobsdispatch that asks Dynamo chat completions fornvext.extra_fields=["prompt_logprobs"]. Dynamo #9509 currently exposesengine_data/ completion token data, notnvext.prompt_logprobs, so copying that prime-rl path would require a matching Dynamo change first.Validation
Local:
uv lock --checkuvx ruff==0.13.0 check --config=pyproject.toml src/prime_rl/utils/client.py tests/unit/utils/test_client.pyuvx ruff==0.13.0 format --check --config=pyproject.toml src/prime_rl/utils/client.py tests/unit/utils/test_client.pyGitHub Actions:
Local test note:
uv run pytest tests/unit/utils/test_client.pyis blocked on macOS by the repo's Linux-only lockfile;uv run --no-sync pytest tests/unit/utils/test_client.pyexited 139 locally.