Repository navigation
Advance development to 0.11.0.dev0 and freeze rollout baseline - #91
Merged
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.Su
2DE9
ggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
0.10.2.dev0to0.11.0.dev0while stable remains immutablev0.10.1hf_referenceactor-rollout baseline across 24 prompt/response/n/sampling cellsMeasured baseline
0d6e0070ae73ef35f718aec3624ee5263ac96e3a0256bd9e63ca6ed52999a5073a3577a008581a8d4418062314750d86f21cd5fe2e303eabb559b843d25377a7c72e0aeb0219eec7eb8bc109c0419839b3251170b25daee7ee726b7a7be18d7dbe26590fb61325bf212cfd9e7110b69f5fa8889cThe result is rollout-only. Prefill/decode/TTFT boundaries, teacher scoring, actor update and full-cycle time remain explicitly
not_measured;n=4is repeated independent requests, not the future typed grouped-sample contract.Validation
ruff check .ruff format --check .mypy src/miniverlpytest -q -m "not gpu and not network" --cov=miniverl2391 passed, 9 skipped, 22 deselected; total coverage84%pytest -q -m gpu:8 passed, 2414 deselectedpytest -q -m network:16 passed, 2406 deselectedpython scripts/check_markdown_links.pypython scripts/check_text_integrity.pypython scripts/release_state.py --checkmkdocs build --strictuvx --from actionlint-py actionlintFrozen calculator SHA-256 remains
53fc1d4d5b7adee09618d77ad62d4086ba56b78569832d6fc7c3bcd5c2695bbc. No existing benchmark, profile identity, tag, model revision or release artifact changed.