-
I wanted to know if it is GPU dependent if the PCIe bandwidth monitoring shows up like it does in your screen shot in the README.
I have a GPD Win4 (Ryzen 7 7840U) and a RX 7900xtx gpu connected.
-
It would be nice of ollama had a /metrics endpoint for collecting metrics for prometheus or other monitoring tools.
https://prometheus.io/docs/guides/go-application/
Some metrics to include migh…
-
**DESCRIPTION:**
We are currently utilizing the `amzn2-ami-ecs-gpu-hvm-2.0.20240109-x86_64-ebs` AMI for our ECS instances. However, we have observed that this AMI lacks support for the [dlami-cloud…
-
Dear Kaelri,
Would you add CPU/core, HDD, and GPU temperature monitoring using this OHM/Open Hardware Monitoring plugin?
> http://rainmeter.net/forum/viewtopic.php?f=18&t=6874
Download link > http:…
-
**Is your feature request related to a problem? Please describe.**
no
Currently, the triton-server provides GPU utilization metrics in Prometheus format, like so:
```
# HELP nv_gpu_utilization G…
-
### Software information
I've been getting very frequent GPU resets (`ring gfx_0.0.0 timeout`) in Warhammer 40k Darktide, making it nearly unplayable. Sometimes I can play 4 games without any crash…
-
### Issue description
We use the node-feature-discovery and gpu-feature-discovery features to monitor GPU issues, including cases when the number of available GPUs on a node unexpectedly decreases:…
-
### What is the issue?
We have seen instances where when we use the OpenAI API compatibility layer Ollama fails to utilise our NVIDIA GPU. When we re-run the test using the Ollama generate API it doe…
-
Thanks for writing these scripts!! How would one go about monitoring the training? (i.e. training loss/validation loss/mAP).
Also I am trying to leverage your script to fine tune a different datase…
-
- send metrics to monitoring platform
- create public dashboard access
- users access dashboard
- GPU monitoring
- CPU monitoring