feat(inference): perplexity CLI line-oriented JSON event output

[ohdearquant]

What

eval_perplexity emits a line-oriented @@lattice perplexity event the app can parse.

Why

The Models screen's perplexity readout consumes structured stdout. This adds a single JSON event line ("ev":"perplexity", with the score) alongside the human-readable output. Auto-discovered binary, so it is already covered by cargo build --workspace.

Files

• crates/inference/src/bin/eval_perplexity.rs (+45)

Verification

cargo build --release -p lattice-inference --bin eval_perplexity --features f16,metal-gpu clean. Built green in the integrated-tree gate.

Bench

Binary-only, additive output. make bench-compare's comparator errored assembling the delta (known two-worktree fragility; base benches ran clean) — bench-neutral by construction, as the changed code is off every Criterion-measured path.

Series

Part of the PR #193 engine-slice (finest split). All engine code lands on main; the macOS app surfaces a subset (Models + Chat) for v0.0.1.

[github-actions]

E2E Parity Report

PASS: all 3 prompts match within first 3 tokens

Prompt	Agreement	First Diff	HF tok/s	Lattice tok/s	Verdict
The capital of France is	3/15	pos 3	0.2	1.6	PASS
In the year 2024, artificial intelligence	10/15	pos 9	0.3	1.6	PASS
`def fibonacci(n):

if n <= 1:
    return n
return` | 15/15 | none | 0.3 | 1.0 | PASS |

The capital of France is

• HF: Paris.
  The capital of France is Paris.
  The capital of France
• Lattice: Paris.
  A: Yes, the capital of France is Paris.

In the year 2024, artificial intelligence

• HF: (AI) has become a significant part of the global economy. It is
• Lattice: (AI) has become a significant part of our daily lives. From personal

def fibonacci(n): if n <= 1: return n return

• HF: fibonacci(n-1) + fibonacci(n-2)

print(fib

• Lattice: fibonacci(n-1) + fibonacci(n-2)

print(fib