Which GPU should you actually use for embedding workloads?
Selecting the right serving engine for your embedding model can dramatically outperform hardware upgrades, yielding up to an 11x throughput increase on the same GPU.
All
1. Create Network Storage (2TB), Use the CA-MTL-4 region (recommended for now).
2. Spin Up a Pod using Runpod official Pytorch template and mount the network volume you just created, once the pod is running, connect to Jupyter Lab
3. Download the Model
- In the Jupyter terminal, install the Hugging Face CLI and download the model:
4. Launch the Cluster
- Choose Standard Cluster
- Select the network volume you created
- Set Pod Count to 2 (default is 2)
- Pick H200 SXM GPU type
- Select Runpod Pytorch official template
- Click Edit Template and set container disk size to be 2000 GB
- Click Deploy Cluster to launch it.
1. installation on Node 0 with a shared volume
2. Node 1 Instructions
3. You should see the following:
4. Run on node with ip as host.
Open AI Implementation
Expected Output:
Known Issues
Currently as of July 21st, vllm library is not up to date so need to build from nightly builds.
https://github.com/MoonshotAI/Kimi-K2/issues/19
Gotchas
uv environment on a Network Volume is slow to initialize ray, recommend any python environments be ran on the machine itself instead of on the Network Volume.
Related posts
Author profile: Brendan McKeag
