1.9 KiB
1.9 KiB
Figures Index
Generated by:
.venv/bin/python analysis/characterization/plot_current_results.py
| Figure | Intended Claim |
|---|---|
| fig_full_trace_workload.png | Full GLM-5.1 trace is long-input, short-output, and high input/output ratio. |
| fig_session_skew.png | Session input-token mass is highly skewed; top sessions dominate work. |
| fig_pdsep_vs_combined.png | Existing static PD-sep A/B regresses TTFT/E2E vs combined. |
| fig_elastic_vs_baseline.png | Existing elastic transfer-based run does not improve TTFT/TPOT over high-contention baseline. |
| fig_gpu_balance.png | Existing runs show GPU-util imbalance, but more data is needed for hot-spot causality. |
| fig_claim_status.png | Current audit separates supported, partial, and unsupported claims. |
Figure Previews
Full Trace Workload
Full GLM-5.1 trace is long-input, short-output, and high input/output ratio.
Session Skew
Session input-token mass is highly skewed; top sessions dominate work.
PD-Sep vs Combined
Existing static PD-sep A/B regresses TTFT/E2E vs combined.
Elastic vs Baseline
Existing elastic transfer-based run does not improve TTFT/TPOT over high-contention baseline.
GPU Balance
Existing runs show GPU-util imbalance, but more data is needed for hot-spot causality.
Claim Status
Current audit separates supported, partial, and unsupported claims.
