fix(deepseek): reserve rings before KV sizing - #209
Open
vegetabledoww wants to merge 1 commit into
Open
Conversation
|
Important
This repository does not receive automatic reviews because it has fewer than 10 stars. ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
vegetabledoww
force-pushed
the
fix/deepseek-test-ring-depths
branch
2 times, most recently
from
August 29, 2026 02:04
7bac55f to
cc0d8a2
Compare
Pass the per-dispatch RunConfig when creating the persistent DeepSeek worker so its static ring arenas are committed before the KV cache budget is measured. Use the previously validated four-ring EP8 capacities in the accuracy guard and documented commands, avoiding the 8 GiB heap produced by broadcasting a 2 GiB scalar. Advance the pypto-lib gitlink to f56cce2, which contains the DeepSeek-V4 create_tensor init_value migration required by the current PyPTO API.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pass the per-dispatch RunConfig when creating the persistent DeepSeek worker so its static ring arenas are committed before the KV cache budget is measured.
Use the previously validated four-ring EP8 capacities in the accuracy guard and documented commands, avoiding the 8 GiB heap produced by broadcasting a 2 GiB scalar.