vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

memory: correct the util note in the fv-ml1 layout

Browse Source
This commit is contained in:
vh
2026-10-05 22:51:24 -07:00
parent c35f6510bf
commit 2b525cd5c9
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
persistent-memory.md
+1 -1
View File
@@ -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)