AI PCIe Card Integration Assistance & running AI models on installed AI PCIe card (from out of CPU)
Budget: $8 – $15 USD
I require quick assistance to run AI models on my e75 Tenstorrent PCIe card. The main objective is to save CPU resources.
Here are some details -
I Installed Tenstorrent e75 PCIe card, drivers downloaded but AI models are running in CPU and uses CPU power & System RAM.
Installed ollama, but it does not detect AI Accelerator to run AI models which is available under "lspci" in ubuntu
I wanted to move the processing of AI models to PCIe card based on model size and some models can use system ram if model size exceed the PCIe card 8 GB RAM.
You will be provided access to PC.
Deliverables
Successfully running AI models in e75 Tenstorrent PCIe card, releasing CPU usage for other workload.
Here are some details -
I Installed Tenstorrent e75 PCIe card, drivers downloaded but AI models are running in CPU and uses CPU power & System RAM.
Installed ollama, but it does not detect AI Accelerator to run AI models which is available under "lspci" in ubuntu
I wanted to move the processing of AI models to PCIe card based on model size and some models can use system ram if model size exceed the PCIe card 8 GB RAM.
You will be provided access to PC.
Deliverables
Successfully running AI models in e75 Tenstorrent PCIe card, releasing CPU usage for other workload.