- Copy compute_chunked_prefill implementation from FullAttentionPolicy - Set default threshold to 0.95 for accuracy testing - Remove debug code (sys.exit, verbose prints) - Use ring buffer pipeline for historical block loading - Merge with current chunk attention using flash_attn_with_lse RULER NIAH test passed with 5/5 samples (100% accuracy). Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
19 KiB
19 KiB