[Power] Power measurement roadmap

Links

• Dashboard: https://inferencex.semianalysis.com/inference?i_seq=8k%2F1k&i_metric=y_measuredJPerOutputToken
• H200 exact-pin validation: run 32324249431
• Producer: https://github.com/SemiAnalysisAI/InferenceX
• Consumer: https://github.com/SemiAnalysisAI/InferenceX-app
• Producer fork: edwingao28/srt-slurm#2 at e5c837f

Roadmap

Producer

• Single-node fixed-sequence power, NVIDIA + AMD #1558 #2323
• Multinode disaggregated power #2437
• Prefill/decode role watts #2553
• Schema v2 whole-deployment energy semantics #2599
• Single-node AgentX power #2601
• GB200/GB300 FP4 DCGM lanes #2507
• AMD multinode power
• Kimi-K3 power evaluation; retain its current vLLM/external-fork clone route until separately qualified

Multinode rollout [1/5]–[5/5]

• [1/5] Long-lived srt-slurm fork prerequisite (merged 2026-08-24) edwingao28/srt-slurm#2
• [2/5] H200 multinode AgentX infrastructure #2683 (merged 2026-08-24)
• [3/5] H200 GLM-5.2 + DSV4 recipe rollout #2684 (merged 2026-08-24; CI sweep 8/8 = 100%, GLM + DSV4 both publication_valid: true)
• [4/5] GB multinode recipe rollout #2687 — merged 2026-08-25; validation run 32780220262: GB200 qwen c768 + GB200 dsv4 c16384 + GB300 qwen c5120 all required=True status=complete publication_valid=True; dsv4-GB nightly-pin lanes still blocked by rotted images (pre-existing on main)
• [5/5] B200/B300 multinode rollout #2688 — merged 2026-08-26; validation run 32924589757: b200-dgxc + b200-nscale lanes zero failures, b200-nscale-slurm_02 vllm audit required=True complete publication_valid=True (c128/c256 windows valid), B300 both frameworks published valid power; remaining reds attributed to b300-014 enroot perms (cluster ops) and intermittent NIXL; kimik2.6 lanes blocked on runner capacity (also on main)

Multinode rollout validation

• H200 GLM-5.2 strict validation on exact producer e5c837f: run 32324249431 — required: true, publication_valid: true, 32/32 GPUs, schema v2, power_valid: 1
• H200 DSV4 optional recipe validation on producer a1b8c7af: run 32312491367
• H200 CI full validation on e5c837f via #2684: run 32767381601 — 8/8 lanes, GLM disagg + DSV4 agg both status=complete publication_valid=True
• Local and CI contract validation for #2683, #2684, #2687, and #2688
• H200 DSV4 exact-pin refresh on e5c837f (optional; remains required: false)
• H100 SA-Bench dedicated-infrastructure smoke on e5c837f if required for the fork scope
• Native GB hardware validation for #2687
• Native B200/B300 hardware validation for #2688
• After each rollout merge, verify production ingestion and dashboard visibility: schema v2, power_valid scrubbing, whole-deployment J/token semantics, J/query, and role watts where applicable

Power validation series [1/4]–[4/4]

• [1/4] Single-node energy validation #2323
• [2/4] Multinode energy validation #2437
• [3/4] GB200/GB300 official DCGM lane #2456
• [4/4] AMD MI355X strict monitor lifecycle #2494

Upstream srt-slurm

• [1/4] DCGM power artifact data layer #288
• [2/4] Multinode DCGM collection #289 (closed; carried in the fork pin)
• [3/4] Measurement window contract #290
• [4/4] Offline artifact validator + telemetry docs #291 (in review; not a blocker for the long-lived fork)

Dashboard

• Measured energy axes app#720
• Validity guard app#734
• J/query, Wh/query, and %TDP axes app#735
• AI-chart lower-is-better fixes https://github.com/SemiAnalysisAI/InferenceX-app/pull/798