8 Commits

Author	SHA1	Message	Date
kijai	845eb14425	Handle thinking tokens different only for Gemma4	2026-04-13 23:40:52 +03:00
kijai	c857b6c657	Translate think tokens	2026-04-12 21:25:19 +03:00
kijai	0fc398a821	Various fixes	2026-04-12 18:11:07 +03:00
kijai	93e8635110	parity with reference implementation ... outputs can 100% match transformers with same sdpa flags, checkpoint this and then optimize	2026-04-07 01:15:04 +03:00
kijai	832753f497	initial gemma4 support	2026-04-03 03:46:45 +03:00
Jukka Seppänen	404d7b9978	feat: Support Qwen3.5 text generation models (#12771)	2026-03-25 22:48:28 -04:00
comfyanonymous	5f2117528a	Force min length 1 when tokenizing for text generation. (#12538)	2026-02-19 22:57:44 -05:00
Jukka Seppänen	6d11cc7354	feat: Add basic text generation support with native models, initially supporting Gemma3 (#12392)	2026-02-18 20:49:43 -05:00