Sam Partee
Sam Partee
Hello, as the RedisAI team knows, [CrayLabs](https://github.com/CrayLabs) uses RedisAI within SmartSim. Currently we have a few issues that we figured would best be grouped together such that they can be...
**Describe the bug** The pre-built onnx backend provided by RedisAI expects that ``GLIBC_2.27`` is available on the system. Many systems, especially in High Performance Computing (HPC), do not have this....
# Description Not every system/user uses bash for job submission to a scheduler. SmartSim should be able to change the shebang line at the top of the script thats written...
## Description In (https://github.com/craylabs/smartsim/issues/122) the ``_install`` classes were introduced to bring configurable builds of SmartSim. The ``BuildEnv`` class is responsible for checking the environment which includes the perquisites like: -...
# Description Create an automated Spack install for SmartSim. # Justification SmartSim has three external dependencies that could be installed by Spack. Hiredis and Redis are already a part of...
# Description sometimes in a workflow, you only want something to run if the job before it ran successfully without error. This should be possible through a few small additions...
**Describe the bug** I was running [this notebook](https://github.com/triton-inference-server/hugectr_backend/blob/e4f4275e0101f52f2814768db8b063e0f88e0241/samples/wdl/HugeCTR_WDL_Training.ipynb) which uses NVTabular to process the clicks dataset link commonly used as a demo for HugeCTR. When running this notebook, I keep...
**Describe the bug** I was running [this notebook](https://github.com/triton-inference-server/hugectr_backend/blob/e4f4275e0101f52f2814768db8b063e0f88e0241/samples/wdl/HugeCTR_WDL_Training.ipynb) which uses NVTabular to process the clicks dataset link commonly used as a demo for HugeCTR. When running this notebook, I keep...
# Description In order to make SmartRedis ``DataSet`` objects more amenable to activies like online analysis and training, we should investigate data formats that make sense to be able to...
Users should be able to have multiple conversations and within each conversation, the arxiv chatguru should remember the context of the conversation. This will involve changing from the ``RetrievalQA`` chain...