0 Fork 0

Files

T

tzhouamandClaude Fable 5.1 f804bbd679 [Edge][WP0] Record Qwen3-TTS streaming baselines on 1x L20X

Default deploy config (1 -> 25 frame schedule), 12 prompts x 3 repeats,
warm-up excluded, one GPU via `gpu run`:
  1.7B CustomVoice: TTFA p50 32.0 ms, playback-start p50 116 ms (stall at
    TTFA 85 ms), RTF_total 0.086, chunk gap p50 163 ms, init 271 s (cold caches)
  0.6B CustomVoice: TTFA p50 27.8 ms, playback-start p50 95 ms (stall 67 ms),
    RTF_total 0.077, chunk gap p50 146 ms, init 152 s
Per-request chunk arrivals, memory and the full summaries are in the JSON
(force-added: *.json is gitignored repo-wide).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-09 10:49:37 +08:00

stream_latency

[Edge][WP0] Record Qwen3-TTS streaming baselines on 1x L20X

2026-09-09 10:49:37 +08:00

README.md

[Edge][WP0] Add offline streaming-latency benchmark for chunked TTS

2026-09-09 10:24:53 +08:00

README.md

Edge benchmark results

Committed JSON produced by the edge branch benchmarks (kept small; WAVs are never committed):

stream_latency/<model>/<deploy>/<timestamp>[_tag].json — stream_latency_bench.py output (schema 1): meta (model, deploy config, git SHA, GPU), init (init_s, optional init timeline), resources (peak RSS, peak GPU MiB, sampling mode), requests[] (per-chunk arrivals, TTFA, playback-start, stall at TTFA, RTF streamed / total) and summary (p50/p90/max).
init_profile/<timestamp>/summary.json — init_profile.py comparison of initialization phases per configuration.
hw_emulation/, scheduling/ — per-work-package comparison tables.

Metric definitions live in benchmarks/tts/stream_latency_metrics.py.