Liger-Kernel
Liger-Kernel copied to clipboard
Problem when running GRPO with liger kernel.
Hi, thanks for your work. When I run Qwen2.5-VL using GRPO with liger kernel in ms-swift, it happens:
But when I turn --use_liger_kernel into false, it can run correctly. My version: torch: 2.7.1 cuda: 128 transformers: 4.53.2 flash_attn: 2.8.1 liger kernel: 0.6.0
How to solve this? Dose it related to the LigerFusedLinearGRPOLoss? Thanks!