Pepijn aea04721ae feat(annotate): parallelize episodes within each module phase ...

Saturates parallel_servers + client_concurrency. Previously the
executor processed one episode at a time, so each Module 1 episode's
3-5 dependent VLM calls hit a single server with the others idle. Now
defaults to 16 episodes in flight; configurable via
ExecutorConfig.episode_parallelism.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-04-30 18:48:35 +02:00

..

modules

feat(annotate): client_concurrency for parallel in-flight requests

2026-04-30 18:48:35 +02:00

prompts

feat(annotate): Module 1 sees the whole episode as one video block

2026-04-30 18:48:33 +02:00

__init__.py

feat: language annotation pipeline (PR 2/3)

2026-04-30 18:48:33 +02:00

config.py

feat(annotate): parallelize episodes within each module phase

2026-04-30 18:48:35 +02:00

executor.py

feat(annotate): parallelize episodes within each module phase

2026-04-30 18:48:35 +02:00

frames.py

feat(annotate): video_url block for openai backend

2026-04-30 18:48:34 +02:00

reader.py

feat: language annotation pipeline (PR 2/3)

2026-04-30 18:48:33 +02:00

staging.py

feat: language annotation pipeline (PR 2/3)

2026-04-30 18:48:33 +02:00

validator.py

feat: language annotation pipeline (PR 2/3)

2026-04-30 18:48:33 +02:00

vlm_client.py

fix(annotate): probe /v1/models for spawn-helper readiness

2026-04-30 18:48:35 +02:00

writer.py

feat: language annotation pipeline (PR 2/3)

2026-04-30 18:48:33 +02:00