- Remove --max_tokens, let scheduler use max_seq_len - prompt_len - Rename --cache_len to --max_seq_len to match engine naming - Unify sampling defaults to 0.8/50/0.95
- Remove --max_tokens, let scheduler use max_seq_len - prompt_len - Rename --cache_len to --max_seq_len to match engine naming - Unify sampling defaults to 0.8/50/0.95