transformers
2e7033ed - Quiet continuous batching at default verbosity (#48314)

Commit
14 hours ago
Quiet continuous batching at default verbosity (#48314) * Quiet continuous batching at default verbosity A plain generate_batch printed five WARNING lines (attention auto-switch, warmup start/finish, progress-bar note) and a progress bar; generate prints nothing. Status messages move to info, and the progress bar is opt-in. Actionable warnings (unset eos_token_id, warmup failure, dropped requests) stay at warning. * Apply suggestion from @qgallouedec * Apply review: keep the attn switch a warning, TODO for the warmup progress bar
Author
Parents
Loading