Daniel Han 629cc50f1a Unsloth run/start: per-model recommended sampling and override flags (#7335) ... Seed each request with the model's recommended sampling (matching the Chat UI), add per-field override flags, ignore oversized overrides, warn when sampling pins cannot apply to a reused server, and apply pins to the completions endpoint.		2026-07-23 20:49:54 -07:00
..
__init__.py	Final cleanup	2026-03-12 18:28:04 +00:00
inference_config.py	Unsloth run/start: per-model recommended sampling and override flags (#7335)	2026-07-23 20:49:54 -07:00