Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Documentation] Changing suggested SKU to Standard_D8s_v5 #2290

Merged
merged 1 commit into from
Nov 14, 2024
Merged

[Documentation] Changing suggested SKU to Standard_D8s_v5 #2290

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/source/deployment/deploy_sre.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,7 +167,7 @@ As some general recommendations,

- For general purpose use, the D family gives decent performance and a good balance of CPU and memory.
The [Dsv6 series](https://learn.microsoft.com/en-us/azure/virtual-machines/sizes/general-purpose/dsv6-series#sizes-in-series) is a good starting point and can be scaled from 2 CPUs and 8 GB RAM to 128 CPUs and 512 GB RAM.
- `Standard_D8s_v6` should give reasonable performance for a single concurrent user.
- `Standard_D8s_v5` should give reasonable performance for a single concurrent user.
- For GPU accelerated work, the NC family provides Nvidia GPUs and a good balance of CPU and memory.
In order of increasing throughput, the `NCv3` series features Nvidia V100 GPUs, the `NC_A100_v4` series features Nvidia A100 GPUs, and the `NCads_H100_v5` series features Nvidia H100 GPUs.
- `Stanard_NC6s_v3` should give reasonable performance for a single concurrent user with AI/ML workloads.
Expand Down
Loading