Yingcan Wei

When the cache size configured by the user is less than 64, the default value will be used, so this problem will not occur after 22.09

@tuanavu Thanks for your feedback, we have decoupled/reorganized third parties dependency HPS depends on after 23.06. Since we have pre-installed all HPS/SOK related libraries, there is no need to set...

> Hi @yingcanw, following up on this thread, without setting the LD_PRELOAD, I got this error after deploying the model. I used `nvcr.io/nvidia/merlin/merlin-tensorflow:23.09`, do you know how to resolve this?...

> Sure, Steps to reproduce the behavior: > > 1. Train a TF+SOK model with merlin-tensorflow:23.09 and follow the deployment steps outlined in the [HPS TensorFlow Triton deployment demo notebook](https://github.com/NVIDIA-Merlin/HugeCTR/blob/main/hps_tf/notebooks/hps_tensorflow_triton_deployment_demo.ipynb)...

Thank you for your corrections. There is a typo here. We have upgraded python to 3.10 since 23.08, and we need to update the notebook to modify the triton server...

Thanks a lot for your update, I think this error output can be easily misunderstood(we have verified that if the LD_PRELOAD parameter is set, circular dependencies will cause seg fault)....

@tuanavu Regarding the 2rd question, I have some comments here. We already support quantization for fp8 in the static embedding cache from v23.08. HPS will perform fp8 quantization on the...

@lausannel Thank you for your feedback. We are gradually deprecating the ETC-related APIs. HKV will serve as a replacement for ETC. Regarding the use of SOK for training after integrating...

@Lifann Thanks for your feedback. In order to understand your question more accurately. Let me first make it clear that the current GPU cache in HPS is only used for...

@hsezhiyan The ETC will be be replaced by [HierarchicalKV](https://github.com/NVIDIA-Merlin/HierarchicalKV) on the training using hierarchical memory. We actually have no plans to integrate the GPU embedding cache into training. In addition,...