Jiayu Chang comments

Repositories
Issues
Comments

Results 12 comments of


                                            Jiayu Chang

[https://nvbugs/5322131][feat] Multi-LoRA serving with CUDA Graph

/bot run --disable-fail-fast

[https://nvbugs/5322131][feat] Multi-LoRA serving with CUDA Graph

> Does the change also affect the runtime w/o CUDA graphs? (`no CUDA Graph + multi LoRA (after changes)`) It should not as we keep the same legacy LoRA code...