From 2b525cd5c960c2fad12953fec0ac089f742f47c6 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Mon, 5 Oct 2026 22:51:24 -0700 Subject: [PATCH] memory: correct the util note in the fv-ml1 layout --- persistent-memory.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/persistent-memory.md b/persistent-memory.md index 663a16e..4136899 100644 --- a/persistent-memory.md +++ b/persistent-memory.md @@ -166,7 +166,7 @@ _As of 2026-10-05 ~2035 PT. The newest subsection is first; older subsections ca | 1 | intern-decision | 32,768/call | cap 14.4 GiB, peak 15,220 | — | — | | 2 | flash-next (gen, gen-large, +6) | 262,144 | — | 344,155 | 1.31× | -Every vLLM seat on a shared card (GPU 0, GPU 1) has byte-pinned KV (`--kv-cache-memory`), so util only gates the boot check and is set just above each footprint. flash-next is alone on GPU 2 and stays util-sized (0.96). +Every vLLM seat on a shared card (GPU 0, GPU 1) has byte-pinned KV (`--kv-cache-memory`), so util only gates the boot check (Free at start ≥ util × total). flash-next is alone on GPU 2 and stays util-sized (0.96). - **GPU 3:** clear for ad-hoc work (Prime, 2026-10-05); no always-resident tenant goes here. On-demand tenants: Blender, Scriberr (0 idle, ~5.5 GB per job), and MIA auto-rig (one-shot `scripts/mia-run`, peak 3.4 GB, added 2026-10-01 for dread-dev). When a full-size seat claims GPU 3, Scriberr steps aside to **irv-ml1's A6000**, not back to GPU 1. ### intern-decision (replaced SemIf on 2026-09-30)