Matthias Reso
Matthias Reso
## Description This PR adds an example showing how to create and deploy a single GPU DLRM example with TorchRec. Because the current TorchRec version 0.2.0 needs Pytorch 1.12.0 this...
## 🐛 Bug **Describe the bug** Hi, I've scripted a Roberta model and when I do two inference calls on it, the second call returns a result only after several...
## 🐛 Bug **Describe the bug** When saving a scripted tokenizer with torch.jit.save and loading it with torch.jit.load while giving a gpu device as map_location the program crashed with a...
## Description Please read our [CONTRIBUTING.md](https://github.com/pytorch/serve/blob/master/CONTRIBUTING.md) prior to creating your first pull request. Please include a summary of the feature or issue being fixed. Please also include relevant motivation and...
## Description Please read our [CONTRIBUTING.md](https://github.com/pytorch/serve/blob/master/CONTRIBUTING.md) prior to creating your first pull request. Please include a summary of the feature or issue being fixed. Please also include relevant motivation and...
## Description This PR follows https://github.com/pytorch/serve/pull/2219 and refactors the sanity checks to use pytest ## Type of change Please delete options that are not relevant. - [X] New feature (non-breaking...
### 🚀 The feature currently we only accept .pt file ### Motivation, pitch requires less steps to try it out + image compression on transfer ### Alternatives _No response_ ###...
### 🚀 The feature Our cpp unit tests contain a couple of pt files without documentation how they were create or what they contain. Reconstruct the info and create a...
### 🚀 The feature Improve discoverability of our exampels. ### Motivation, pitch We've heard from several sides now that our list of examples are confusing and hide valuable topics and...
### 🚀 The feature Update cpp/llamacpp to Llama 3 ### Motivation, pitch Update cpp/llamacpp to Llama 3 ### Alternatives _No response_ ### Additional context _No response_