chore: sync upstream (thinking_retention #88, fastokens removal #95, dyn-versioning #96) + migrate gemma4#10
Merged
Conversation
…pected by the bridge (PrimeIntellect-ai#88)
…-thinking-retention # Conflicts: # .github/workflows/publish-dev.yml # pyproject.toml
joanvelja
force-pushed
the
chore/sync-upstream-thinking-retention
branch
from
85ad64e to
197a9f0
Compare
…ate hot path 1:1, full-render keeps thinking) + fastokens test fix
joanvelja
force-pushed
the
chore/sync-upstream-thinking-retention
branch
from
197a9f0 to
86afca1
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Syncs renderers fork to upstream main (3 commits: PrimeIntellect-ai#88 thinking_retention refactor, PrimeIntellect-ai#95 remove fastokens, PrimeIntellect-ai#96 dynamic versioning). Conflicts: only 2 versioning config files (resolved take-upstream). client.py untouched upstream (routed-experts safe).
gemma4 (fork-only) migrated to the new thinking_retention API (render + bridge, matches glm5/deepseek_v3 idiom; implied='all'). Proven via real differential rendering vs current (gemma-4-26B tokenizer, 16 convos x 3 policies):
qwen35 differential verification in progress (separate; PrimeIntellect-ai#88 also touched it).