Add max_anchors random chain sampling to P-EAGLE - #2
Closed
orestis-z wants to merge 1 commit into
Closed
Conversation
2 tasks
|
All links are now valid - this issue has been resolved. Marked as resolved: 656960f |
orestis-z
force-pushed
the
peagle-streaming
branch
from
June 29, 2026 13:07
68bf3ea to
bf9324d
Compare
Randomly subsamples COD chain starting points when max_anchors is set, reducing depth-1+ token count while keeping depth-0 as the full sequence. Combined with streaming attention, this gives ~24x attention reduction for long sequences. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Orestis Zambounis <orestis.zambounis@gmail.com>
orestis-z
force-pushed
the
peagle-max-anchors
branch
from
June 29, 2026 13:09
cc7940d to
656960f
Compare
Owner
Author
|
Superseded by vllm-project#687 (standalone max_anchors) and vllm-project#683 (streaming). |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
max_anchorsparameter to P-EAGLE's COD sampling to randomly subsample chain starting points at depth 1+Changes
data.py: random subsampling ofall_valid_indiceswhenmax_anchorsis set, with.sort()[0]to maintain causal orderconfig.py: newmax_anchors: int | Nonefieldcore.py: wiremax_anchorsthrough forward andfrom_training_argstrain.py:--max-anchorsdefault changed from 256 to Nonedflash/core.py: handle None default withor 3072fallbackTest plan
generate_cod_sample_indiceswith max_anchors (tests/unit/models/test_peagle_data.py)🤖 Generated with Claude Code