nim-anywhere

nim-anywhere copied to clipboard

lleaver

llm-nim-0.sh and llm-nim-1.sh should source model and gpus from variables.env

1

Variables.sh defines the model and the GPUs to use but those values are ignored by the llm-nim-x.sh scripts.

freemansoft

AI Workstation doesn't shutdown redis or milvusdb containers when you stop the environment

1

## Expected behavior All nim-anywhere containers exit when the `project-nim-anywhere` container exits or when `AI Workstation` executes a `stop environment` ## Actual behavior `redis` and `milvusdb/milvus` both continue to run...

freemansoft

Does not run on Titan RTX - demands Bfloat16

2

Received this message starting the LLM. ``` ValueError: Bfloat16 is only supported on GPUs with compute capability of at least 8.0. Your NVIDIA TITAN RTX GPU has compute capability 7.5....

freemansoft

I had a user trying to start the project who got confused at what to put for those configuration interstitials for the docker socket and for the local NIM cache....

nv-edwli

What is the rationale behind why the pyPDF package is a separate installation within the `upload_docs.ipynb` jupyter notebook. Why don't we enable AI Workbench to take care of the installation...

nv-edwli

When I followed the instruction to do a Windows install of NVIDIA AI Workbench, I mistakenly selected podman rather than docker as my container runtime. Then when I followed in...

mrpointzby

how to fill-in ENVIRONMENT for Windows version

5

Hi, Is this project compatible with AI workbench for Windows ? If YES, for host mount, what is the Windows "Source Directory" for Docker with WSL setup ? Description What...

jear

We probably should have the timeout for NIM startup to be as long as it takes for the 8b model to start from an empty NIM cache and without the...

rmkraus

PDFs are out of date within the JupyterLab

1

I asked about the latest datacenter GPU, and it gave me A100 with embedding and reranking, when I turned off, it gave me H100, nothing about blackwell.

arharpster99