2 Commits

Author	SHA1	Message	Date
Wing Lian	ac77da96da	use smaller pretrained models for ci (#3620) [skip ci] ... * use smaller pretrained models for ci * more steps for loss check * fix tests * more train steps * fix losses	2026-04-27 13:22:56 -04:00
Wing Lian	00dee05fc6	support flattening/packing for GRPO (#3552) ... * support flattening/packing for GRPO * more flattening * fix tests * improve dead vllm handling * refactor out process handling for vllm serve and move bench flattening tests to gpu tests * add validation for flattening with liger * isolate batch flattening test * flaky test	2026-03-28 13:15:54 -04:00