Skip to content

Add support for H200 NVL GPUs#2123

Open
cityofships wants to merge 1 commit intostackhpc/2025.1from
add_nvidia_h200
Open

Add support for H200 NVL GPUs#2123
cityofships wants to merge 1 commit intostackhpc/2025.1from
add_nvidia_h200

Conversation

@cityofships
Copy link
Member

03:00.0 3D controller [0302]: NVIDIA Corporation GH100 [H200 NVL] [10de:233b] (rev a1)

03:00.0 3D controller [0302]: NVIDIA Corporation GH100 [H200 NVL] [10de:233b] (rev a1)
@cityofships cityofships requested a review from a team as a code owner February 4, 2026 09:16
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request adds support for NVIDIA H200 NVL GPUs by defining it in stackhpc-compute.yml and adding a corresponding release note. The changes are straightforward and correct. I've provided a couple of minor suggestions to improve consistency and fix a grammatical error.

Comment on lines +123 to +124
h200:
resource_name: "{{ h200_resource_name | default('h200') }}"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For better clarity and consistency with other GPU definitions in this file (e.g., h100_80_sxm, a100_80_sxm), it would be more descriptive to name this entry h200_nvl instead of just h200. This makes it clear that this definition is for the NVL variant of the H200 and avoids potential ambiguity if other H200 variants are added in the future.

  h200_nvl:
    resource_name: "{{ h200_nvl_resource_name | default('h200_nvl') }}"

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I actually agree with gemini here

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looking at the file, the trend seemed to be just SXM versions having their suffix

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think that's just because we don't have any NVL cards in the list yet

---
features:
- |
Adds a definitions for ``NVIDIA H200 NVL`` to the
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

There's a minor grammatical error here. It should be 'Adds a definition' (singular) instead of 'definitions' (plural).

    Adds a definition for ``NVIDIA H200 NVL`` to the

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants