From dfe3f345d88290cbbec235f16864f6e16c0611e9 Mon Sep 17 00:00:00 2001 From: Gahow Wang Date: Mon, 20 Jul 2026 18:15:03 +0800 Subject: [PATCH] research: record workload sweep launch --- .../frontier-workload-regime-taxonomy-20260720.md | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/.research/experiments/frontier-workload-regime-taxonomy-20260720.md b/.research/experiments/frontier-workload-regime-taxonomy-20260720.md index 72360ee..252e3e7 100644 --- a/.research/experiments/frontier-workload-regime-taxonomy-20260720.md +++ b/.research/experiments/frontier-workload-regime-taxonomy-20260720.md @@ -158,3 +158,18 @@ The accompanying mock figure is schematic, not data. Panel A shows the state kne - Full-trace overload can collapse all configs to similarly poor latency. Such points identify a capacity-limited region but cannot validate fine-grained ranking. - MNS ties and censored/failed requests can create false winners; exclude invalid cells before calculating regret and report the exclusion. - One trace cannot establish generality. The initial result is a mechanism boundary for this trace/model/hardware, followed by held-out Q235 validation. + +## Execution log + +### 2026-07-20: materialization and simulator launch + +- Code baseline: `feature/sim@157bf36` for the valid v4 sweep. +- Hosts probed: `dash1`, `dash2`, `dash3`, `dash4`; each exposed 8 NVIDIA H20 GPUs with 0 MiB used at probe time. `dash0` was not probed or used. +- Source cohort: 129 Q30 Trace-PD requests. The private artifact supplies exact prompts, lengths, outputs, timestamps, sessions, and runtime block identities; the simulator projection retains only the first `floor(ISL/16)` complete block identities. +- Materialized: 35 cases = W0--W6 × `rho {0.05,0.25,0.50,0.90,1.20}`. Audit passed request count, exact decode offered load, empirical arrival rate, prefix block count, and prefix-off empty identity vectors. +- Simulator smoke: W0 / `rho=0.05` / TP4-MNS64 completed 129/129. Simulator TTFT mean/p90 was 109.81/124.16 ms and TPOT mean/p90 was 36.26/36.79 ms. This is a harness check, not real-system fidelity evidence. +- Invalid attempts retained for audit: v1 had a Bash argument-expansion error; v2 mixed multiple workload families into a runner that requires strictly increasing anchors from one family; v3 exposed a scikit-learn cache-version mismatch. None is used as scientific evidence. +- Valid v4 controls: isolated output/predictor cache per TP/prefix group; scikit-learn 1.9.0 matching the predictor cache format; per-family five-point runner invocations; stage batch ledger enabled; TP1 exempted from the collective fallback gate because a single rank has no all-reduce. +- Active v4 allocation: dash1=TP1 prefix off/on, dash2=TP2 prefix off/on, dash3=TP4 prefix off, dash4=TP4 prefix on. The four fleet jobs are running from fresh `sim-v4` output roots. First-process audit found the explicit isolated `--metrics_config_cache_dir` on all hosts and zero cross-version warnings. + +Current decision: wait for the v4 simulator state/ranking knees, then select only discriminating real-machine pilot points. No real latency result from vLLM 0.20.2 will be compared with the historical vLLM 0.20.0 baseline until the runtime-version gate is resolved.