From d10fad064e23492874dbdb32c9f888f01d988525 Mon Sep 17 00:00:00 2001 From: Ilker Manap Date: Wed, 30 Sep 2026 20:25:50 +0200 Subject: [PATCH] Mark facility steps 1-5 deferred; node sensors collected Co-Authored-By: Claude Opus 5.5 (1M context) --- docs/facility-aware-placement.md | 4 +++- llmgw-plan.md | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/docs/facility-aware-placement.md b/docs/facility-aware-placement.md index 953eb852..a57efab1 100644 --- a/docs/facility-aware-placement.md +++ b/docs/facility-aware-placement.md @@ -1,6 +1,8 @@ # Facility-aware placement: rack power, temperature and cooling -**Status: planned; its first step, reading the nodes' own sensors, is built.** +**Status: step 0, reading the nodes' own sensors, is built; steps 1–5 are +deferred** until the rack, PDU and power information of a real site is at +hand — without it they would be designed against guesses. This is the design for step 5 of resource allocation, after reserved CPU cores and memory (1), capacity classes and preemption (2), tenant capacity quotas (3) and sizing by measured throughput (4), all of which shipped in v0.10.5. Of diff --git a/llmgw-plan.md b/llmgw-plan.md index 926b2724..efc9b241 100644 --- a/llmgw-plan.md +++ b/llmgw-plan.md @@ -1485,9 +1485,11 @@ The launch path is now built too: - [x] Capacity quotas per organization, team and project: guarantees kept, borrowing taken back, limits enforced - [x] CPU cores reserved like memory, and memory required of CPU models +- [x] Node sensors collected: GPU temperature, power and throttling, CPU + temperature and RAPL power, board inlet air; published and shown - [ ] Rack power, temperature and cooling as placement signals: planned in [docs/facility-aware-placement.md](docs/facility-aware-placement.md), - in five steps from rack spreading to opt-in shedding + deferred — it needs each site's rack, PDU and power data first - [ ] Defragmentation for large tensor-parallel replicas across NVLink domains - [ ] Control plane HA (Raft) - [x] Weight downloading and cache management: the mirror, agent fetches