sigilant-runner · Phi-3.5-mini-instruct · L4 · vllm · 2 configs

Config | TPS | TPS p95 | TTFT | TTFT p95 | ITL | PPL | TPS% | TTFT% | PPL% | Score
INT8_W8A8 · ctx:16384 · kv:k16v16 · long  <- best | 140.9 | n/a | 978.0 | n/a | 7.12 | 2.90 | 100.0 | 100.0 | 100.0 | 100
INT8_W8A8 · ctx:8192 · kv:k16v16 · default | 103.7 | n/a | 1328.7 | n/a | 9.68 | 2.90 | 73.6 | 73.6 | 100.0 | 87

Best config: INT8_W8A8 · ctx:16384 · kv:k16v16 · long
Auto baseline compare: score Δ=0.00 TPS Δ=0.00 TTFT Δ=0.0ms PPL Δ=0.00
Confidence: target=medium gap_before=13.00% var_before=n/a% replay=False(disabled) gap_after=13.00%

PPL is a quality proxy, not production validation.
Full production safety and long-context certification require Sigilant Optimizer.
