Repository navigation
docs: record v1.1.9 frame-cap and GPU A/B results - #34
Merged
Merged
Conversation
The PR #33 GPU A/B passed (G1 corpus captures byte-identical, G2, G3), and the issue #32 diagnostic gave the same frame-cap outcome on v1.1.9 as on the previous pin (tagged 3/5 capped, untagged 0/5, per-reply bytes, durations and RMS identical). I replace the untested/pending wording in README-dialogue, README and CHANGELOG. The cause stays open in #32; the Mac line is unchanged.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Docs-only follow-up to #33.
The PR #33 GPU A/B on CUDA (DGX Spark) passed: G1 corpus captures byte-identical, G2 request sampling pass, G3 tagged and untagged dialogue pass. The #32 frame-cap diagnostic (seeds 1–5) gave the same result on both trees: tagged dialogue capped 3/5, untagged 0/5, with per-reply bytes, durations and RMS identical. So the limit is unchanged on v1.1.9; the cause stays open in #32.
What I change:
recipe/README-dialogue.md: the known stopping limitation now says it was measured on the previous pin and on v1.1.9 with the same outcome. The relabel and no-catalog variations are marked previous-pin only, since I didn't rerun them. The anchorknown-full-model-stopping-limitationis unchanged.README.md,CHANGELOG.md: I drop "GPU A/B pending" and "when measured on the previous pin" and say the A/B passed and the limit is unchanged on v1.1.9.recipe/README-macos.mdis untouched; the Mac build still hasn't run.Checks on this head:
python3 -m unittest discover -s recipe -p 'test_*.py'(50 tests OK, 15 skipped),python3 bench/stream_check.py --self-test(passed),git diff --check(clean). No hosted CI runs on this repo.