mirror of
https://github.com/vladmandic/automatic
synced 2026-08-31 09:31:00 +02:00
CalamitousFelicitousness
f431141d2f
Add optional LLM generation parameters to the VQA API request model, allowing per-request override of settings: - max_tokens, temperature, top_k, top_p, num_beams, do_sample - thinking_mode, prefill, keep_thinking, keep_prefill Changes: - Add 10 new optional fields to ReqVQA model with descriptive docs - Update get_kwargs() to support per-request overrides via singleton - Add helper functions get_keep_thinking(), get_keep_prefill() - Update post_vqa endpoint to pass generation kwargs - Add _generation_overrides instance variable to VQA class