From 7ea96358788c54f3d8a5f9bd5178c34ba3fe7973 Mon Sep 17 00:00:00 2001 From: Gahow Wang Date: Sun, 19 Jul 2026 01:45:17 +0800 Subject: [PATCH] Record fixed PD pressure calibration result --- .../fixed-pd-pressure-matching-card.md | 37 ++++++++++++++++++- 1 file changed, 35 insertions(+), 2 deletions(-) diff --git a/runs/frontier-fidelity-envelope-v1/fixed-pd-pressure-matching-card.md b/runs/frontier-fidelity-envelope-v1/fixed-pd-pressure-matching-card.md index 97b74ca..2efedad 100644 --- a/runs/frontier-fidelity-envelope-v1/fixed-pd-pressure-matching-card.md +++ b/runs/frontier-fidelity-envelope-v1/fixed-pd-pressure-matching-card.md @@ -1,7 +1,7 @@ # EXP-SIMFID-Q30-FIXED-PD-PRESSURE: calibrate a nontrivial fixed-shape workload -> Status: planned. This is a real-only workload calibration; its measurements -> are not part of a Frontier-versus-vLLM winner comparison. +> Status: complete (2026-07-19). This is a real-only workload calibration; its +> measurements are not part of a Frontier-versus-vLLM winner comparison. ## Question @@ -54,3 +54,36 @@ This selects a workload regime, not a simulator parameter and not a serving capacity point. It may make Fixed-PD more comparable to Trace-PD in batching pressure, but it deliberately continues to exclude trace-shaped arrivals and prefix reuse; those are separately evaluated workload dimensions. + +## Result + +All 12 planned cells completed (`257` requests × `3` fresh-server trials per +rate, zero client failures). The raw artifact is +`dash0:/home/admin/cpfs/wjh/aituner/qwen30-fixed-pd-pressure-20260719-r5`; +it records the vLLM version, model/config checksums, H20 inventory, FlashInfer +workspace, and an artifact checksum manifest. Pooled results are: + +| Global / per-GPU rps | TTFT mean / p90 (ms) | TPOT mean / p90 (ms) | E2E mean / p90 (ms) | In-flight proxy | +|---|---:|---:|---:|---:| +| 4 / 1 | 121.53 / 125.12 | 10.75 / 11.83 | 2862.42 / 3138.92 | 11.45 | +| 4.5 / 1.125 | 122.76 / 126.29 | 11.76 / 12.55 | 3122.32 / 3322.26 | 14.05 | +| 5 / 1.25 | 125.09 / 129.66 | 15.16 / 16.58 | 3989.73 / 4354.22 | 19.95 | +| 6 / 1.5 | 129.27 / 134.69 | 21.33 / 23.03 | 5569.14 / 6005.12 | 33.41 | + +The predeclared two-metric rule picks `4.5` global rps (`1.125` rps/GPU), but +that is only the *least mismatched* tested point: TTFT is still 50.1% below +the Trace-PD target (122.76 vs 245.95 ms), while TPOT is 10.7% below it (11.76 +vs 13.18 ms). Raising load to 5 global rps moves TPOT past target (+15.0%) +while TTFT barely changes (125.09 ms); at 6 global rps TPOT is +61.9% while +TTFT remains 47.4% below target. Trial-level mean standard deviations are at +most 0.78 ms for TTFT and 0.34 ms for TPOT, so this is not trial-order noise. + +**Conclusion:** `4096 -> 256` with uniform no-prefix arrivals cannot be called +a pressure-matched Fixed-PD control simply by setting RPS. It has much shorter +request residence time (3.12 s versus 44.99 s) and lower concurrency (14.05 +versus 38.69 by the same Little-law proxy) at its closest point. For the +paper's fixed-versus-trace comparison, retain this case only as a deliberately +different fixed-shape workload; do not interpret any simulator gap as being +caused solely by trace fidelity. A future pressure-matched fixed control must +also increase output length (or otherwise preserve residence time), then repeat +this real-only calibration before reopening the Frontier-versus-vLLM surface.