-
@mlissner @legaltextai As we agreed here we can discuss about the architecture for the microservice to generate the embeddings required for semantic search.
From my understanding we'd require two s…
-
## Issue description
GPU-specific DDX such as `intel` or `amdgpu` are redundant with the generic modesetting DDX and can cause issues such as https://github.com/NixOS/nixpkgs/issues/342763.
We s…
Atemu updated
2 weeks ago
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Environment
```markdown
- Milvus version: 2.4.12
- Deployment mode(standalone or cluster): both
- MQ type(ro…
-
### 🚀 The feature, motivation and pitch
The feature request is to add support for a load/unload endpoint/API in vLLM to dynamically load and unload multiple LLMs within a single GPU instance. This …
-
Hi,
apologies if I have missed this in the documentation.
Is there aw way to make funnel start a docker container using the --gpu xx or --gpu all argument (xx=number of GPUs to use)?
I am passing j…
-
It's called GPU Instancing or Hardware instancing.
Here is a video showing how it can improve performance of rendering more meshes (Unity Example)
https://www.youtube.com/watch?v=fryX28vvHMc
Fr…
-
Here's a sample REST for a VM with GPUs:
```
"guestAccelerators": [
{
"acceleratorType": "projects/code-story-blog/zones/europe-west1-b/acceleratorTypes/nvidia-tesla-k80",
"ac…
-
bootstrap-vz can currently not bootstrap [EC2 GPU instance](http://docs.aws.amazon.com/AWSEC2/latest/UserGuide/using_cluster_computing.html) AMIs. The appropriate drivers should maybe also be installe…
-
-
**Is your feature request related to a problem? Please describe**.
GPU support for container based workloads, predictions using small machine learning models, e.g. a few GPUs and few dozens GBs o…