Repository navigation
Implement lookahead prefetching and wired memory limit probe - #19
Merged
Merged
Conversation
added 2 commits
July 20, 2026 18:52
- Added `lookahead_ab_probe.py` for A/B testing of lookahead prefetching. - Enhanced `_run_one` in `bench.py` to support lookahead prefetching. - Updated CLI to include `--lookahead` option for enabling lookahead. - Modified `StreamingEngine` to incorporate lookahead prefetching logic. - Introduced non-blocking peek method in `PieceCache` for core residency checks. - Added new server endpoints for handling Anthropic-style messages. - Created tests for lookahead functionality ensuring bit-identity and non-blocking behavior. - Bumped version to 0.12.0 to reflect new features and improvements.
- Implemented `wired_limit_probe.py` to investigate the impact of wired memory limits on performance, including detailed logging and metrics collection. - Introduced command-line options for budget sweeps, token counts, and output file management. - Added tests in `test_wire_limit.py` to ensure the engine respects wired memory limits by default and honors opt-out configurations. - Verified that the wired memory limit is applied correctly during engine initialization and that no attempts are made to wire memory when opted out.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.