forked from mooncake-track/Mooncake
Lead the README with the scaling result and a '6 agents, one prefill' hero, add a 'what's new' contribution table, and embed the architecture and result figures into the README and report. demo.sh now prints a one-glance before/after scoreboard (raw stats behind DEMO_VERBOSE), captured in docs/demo_scoreboard.txt. Metric framing is kept unambiguous: 'total prefill work avoided' and 'redundant prefill eliminated' are reported as distinct numbers, and warm-store vs cold-start regimes are labelled so they cannot be misread as conflicting. Co-Authored-By: Claude <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| figures | ||
| REPORT.md | ||
| demo_scoreboard.txt | ||
| stage2_kvbench.txt | ||