Merlin project demo6/3/2023 ![]() Now users only have to pass DataSourceParams once when creating a solver. Simplified DataSourceParams so that users do not need to provide all the paths before they are really necessary. For more information, please refer to the HugeCTR to ONNX Converter information in the onnx_converter directory of the repository. ONNX converter enhancement:: We enable converting MultiCrossEntropyLoss and CrossEntropyLoss layers to ONNX to support multi-label inference. HugeCTR documentation on web page: Now users can visit our web documentation. See the MMoE sample in the samples/mmoe directory of the repository to learn the usage. Joint loss and multi-tasks training support:: We support joint loss in training so that users can train with multiple labels and tasks with different weights. Now users can install SOK via pip install merlin-sok. For more information, please refer to the samples directory of the HugeCTR backend for Triton Inference Server repository. Hierarchical Parameter Server Triton Backend: The HPS Backend is a framework for embedding vectors looking up on large-scale embedding tables that was designed to effectively use GPU memory to accelerate the looking up by decoupling the embedding tables and embedding cache from the end-to-end inference pipeline of the deep recommendation model. For more information, please refer to Hierarchical Parameter Server and HPS Demo. Besides, we prodvide HPS Python APIs and demonstrate the usage with a notebook. ![]() HPS interface encapsulation and exporting as library: We encapsulate the Hierarchical Parameter Server(HPS) interfaces and deliver it as a standalone library. ![]()
0 Comments
Leave a Reply. |