LM Studio API TTFT not captured by grade_run.py (key-name mismatch) — needs a fix to the script.
Detail audit pending a full read, but tests pass and the concurrency model is correct (N create_task workers + Semaphore, proper drain via queue.join + running-count, cancel + gather).
▮ RECOMMENDED USE
DECISIVE: passes the TTS pipeline that Qwen 6-bit couldn't even parse. Uses REAL bounded concurrency (N worker tasks + Semaphore) — exactly Qwen's fatal flaw avoided. Gemma generalizes to multi-task orchestration where Qwen fails. Strong offload candidate for queue/pipeline work.
▮ REFACTORED PATCH
# TTFT capture: LM Studio returns timing under 'stats' or 'timings' with keys like
# 'time_to_first_token' / 'prompt_progress' — grade_run.py should dump resp['stats'] raw
# once to find the right key, then parse it.