Pedro Redondo Loureiro comments

Repositories
Issues
Comments

Results 3 comments of


                                            Pedro Redondo Loureiro

GPU memory is not released by Triton

@AymanAtiia @susnato But does those work with pytorch or onnx models that are exported to tensorRT plan?

Does ensemble model release CUDA cache?

@zeruniverse im having similar issues, where are you setting the ENABLE_CACHE_CLEANING = true and memory.enable_memory_arena_shrinkage = "cpu:0;gpu:0"? In the config.pbtxt?

Pedro Redondo Loureiro

GPU memory is not released by Triton

Does ensemble model release CUDA cache?

How to set cuda-memory-pool-byte-size and handle the case when we are out of this memory