Skip to content

Fix GPU offload split configuration#89

Merged
ncoghlan merged 2 commits intomainfrom
gpu-offload-config
May 27, 2025
Merged

Fix GPU offload split configuration#89
ncoghlan merged 2 commits intomainfrom
gpu-offload-config

Conversation

@ncoghlan
Copy link
Copy Markdown
Contributor

  • client API and server API described strategies differently (favorMainGpu on the client is a specific case of priorityOrder on the LM Studio server)
  • also add test cases for the reverse server to client config mapping (this picked up an error in handling checkbox fields)

Closes #88

* client API and server API described strategies differently
  (favorMainGpu on the client is a specific case of priorityOrder
  on the LM Studio server)
* also add test cases for the reverse server to client config
  mapping (this picked up an error in handling checkbox fields)

Closes #88
@github-actions github-actions bot added the CLA signed Indicates that all contributors have signed label May 26, 2025
@ncoghlan
Copy link
Copy Markdown
Contributor Author

While the PR includes unit tests, it is in draft pending manual testing configuring an actual model load.

@ncoghlan ncoghlan marked this pull request as ready for review May 27, 2025 01:59
@ncoghlan
Copy link
Copy Markdown
Contributor Author

Manual testing was also successful: #88 (comment)

@ncoghlan ncoghlan merged commit 0d9ef67 into main May 27, 2025
10 checks passed
@ncoghlan ncoghlan deleted the gpu-offload-config branch May 27, 2025 02:10
@github-actions github-actions bot locked and limited conversation to collaborators May 27, 2025
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

CLA signed Indicates that all contributors have signed

Projects

None yet

Development

Successfully merging this pull request may close these issues.

gpuOffload config parameter does not work

1 participant