infra/llama-cpp: benchmark report + -fa flag fix

Phase 7 of the vision-LLM benchmark plan. Adds:

- docs/benchmarks/2026-05-10-vision-llm.md — curated report (TL;DR,
  per-model analysis, top-N agreement, cost vs cloud APIs, sample
  captions). Verdict: qwen3vl-4b for the request path (3.55 s p50,
  100% parse, decisive top-N distro); qwen3vl-8b for caption polish.
- docs/benchmarks/benchmark-2026-05-10-1424.json — raw 300-row dump
  for diff-checking against future runs.
- main.tf: -fa -> -fa on (b9085 llama.cpp removed the no-value form
  of the flash-attention flag; without the value llama-server exits
  before serving any request).
- llama-cpp.md architecture doc links the report so future operators
  land on the deployed-and-evaluated model from one entry point.

300/300 calls, 0 parse errors, 33m32s wall on a single T4 with the
GPU exclusively allocated. immich-ml was scaled to 0 for the run
(node1 RAM constraint, not GPU - bumping node1 RAM is tracked as a
follow-up).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

docs/architecture/llama-cpp.md

@@ -14,6 +14,11 @@ choosing between **Qwen3-VL-8B**, **MiniCPM-V-4.5**, and
 Future consumers (Home Assistant, agentic tooling) can hit the same
 endpoint via LiteLLM at the cluster gateway.
 
+First benchmark run (2026-05-10): see
+`infra/docs/benchmarks/2026-05-10-vision-llm.md`. Verdict: **qwen3vl-4b**
+for the request path (3.55 s p50, 100% parse, decisive top-N
+distribution). qwen3vl-8b for caption polish on top picks.
+
 ## Why llama.cpp + llama-swap (not Ollama)
 
 Verified across 7+7 research/challenger subagents (2026-05-10):