Captures the Phase 10 work in the consolidated perf doc. New section
"Watermarker backend matrix" lists AudioSeal (Meta) and SilentCipher
(Sesame's actual) side by side with measured RTF, capacity, conflicts,
and a per-use-case recommendation table.
Headline: SilentCipher is Sesame's literal production watermarker, now
shipping in pure candle with bit-perfect round-trip on real LibriSpeech
audio (15/15 codes, confidence 1.0000) and ~10× smaller than AudioSeal
(~3M params vs ~30M). The "blow them out of the water" item from the
Sesame gap analysis is closed.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
Updated docs/perf_history.md to reflect the full Phase 8 work:
- New TL;DR has TWO production configs (English-only with --moonshine,
multilingual with default Kyutai). The English path is the new
headline recommendation.
- Captured live Z.AI bench numbers from the new production stack
(Q8 + stream + warmup + Moonshine + thinking-disabled): total_turn
8765 ms vs Phase 6f.q8 era 17145 ms — half the wall-clock latency
end-to-end.
- Phase 8 commit table extended to 8.4 through 8.10.
- Added an STT backend matrix (Kyutai 1B / Whisper-rs / Moonshine)
with measured RTF, build flags, and per-deploy recommendation rows.
Bench command used (single turn, real Z.AI glm-4.5 thinking-disabled,
10.43 s LibriSpeech /tmp/asr_test.flac):
target/release/examples/converse_server \\
--bind 127.0.0.1:18099 \\
--quantized-gguf /tmp/csm_q8.gguf \\
--stream-tts --moonshine \\
--llm-base https://api.z.ai/api/coding/paas/v4 \\
--llm-model glm-4.5 \\
--llm-extra-body '{"thinking":{"type":"disabled"}}'
Server-side timing:
recv_phase 0 ms (Moonshine batch — no parallel STT)
stt_post 332 ms (Moonshine transcribe at EOT)
llm_to_first_audio 1627 ms (Z.AI TTFT ~1.3 s + first TTS chunk)
conv_total 8432 ms
total_turn 8765 ms
Client TTFA: 1959 ms (vs Phase 6f.q8 era ~2 s — comparable; the dominant
remaining latency is the Z.AI provider TTFT, not anything we control).
Z.AI returned a coherent reply: "He eagerly anticipated a hearty stew
with turnips, carrots, potatoes, and savory mutton pieces for dinner."
matching the LibriSpeech ground-truth meaning.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
Consolidated record of every shipped optimization, every rejected path
with the data behind the rejection, the production-recommended config,
the architectural lessons captured, and the deferred multi-session
work with realistic sizing.
Headline:
- client first_audio_ms p50 = 529 ms (mock LLM, Q8 + stream + extended warmup + VAD gate)
- real Z.AI loop: ~2 s TTFA p50
- boot cost: ~2.7 s (one-time)
Rejected paths captured (so future sessions don't redo the work):
Q4_K_M (2.85x slower than Q8), whisper-rs linkage (2-3x CSM regression),
Silero V5 via ort (protobuf 3.14 vs 3.21 conflict), Mimi codec Q8
(no candle conv-quant path), KV cache reuse (variance is content-
dependent not state-dependent), rayon for single-connection
(overhead exceeds gain on <100µs tasks), codec swaps (require
backbone retrain), custom distillation (no published checkpoint),
Kyutai 4x flush (hardware-bound on M-series).
Architectural lessons:
1. In-process linkage of external ML runtimes is a recurring trap;
default to sidecar-process pattern.
2. Bench thermals dominate single-machine A/B; 90s cooldown often
necessary.
3. First-frame compilation is the dominant cold-start cost — long
warm-ups are essential.
4. Conv-phase variance is content-dependent, not state-dependent.
5. tokio::join! polls cooperatively — spawn separate tasks for real
concurrency between sync compute and async pump.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
