Zhang Dong comments

Repositories
Issues
Comments

Results 1 comments of


                                            Zhang Dong

chatGLM 推理时，显存递增直至爆满问题

使用int4，仍然报错，不知道为啥 OutOfMemoryError: CUDA out of memory. Tried to allocate 11.87 GiB (GPU 0; 11.99 GiB total capacity; 9.28 GiB already allocated; 0 bytes free; 10.16 GiB reserved in total by...