Skip to content

refactor: deepen inference model loading#1

Merged
LessUp merged 3 commits into
masterfrom
copilot/model-runtime-deepening
May 22, 2026
Merged

refactor: deepen inference model loading#1
LessUp merged 3 commits into
masterfrom
copilot/model-runtime-deepening

Conversation

@LessUp
Copy link
Copy Markdown
Collaborator

@LessUp LessUp commented May 22, 2026

Summary

  • deepen GPU/resource lifecycle handling and preserve deferred cleanup semantics
  • compile and validate model graphs at load time with atomic model swaps
  • tighten tensor layout/runtime contracts and expand regression coverage

Test Plan

  • npm run lint
  • npm run build
  • npm test

LessUp and others added 3 commits May 22, 2026 10:29
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
@LessUp LessUp merged commit 6b446d4 into master May 22, 2026
@LessUp LessUp deleted the copilot/model-runtime-deepening branch May 22, 2026 02:52
LessUp added a commit that referenced this pull request May 22, 2026
* refactor: deepen inference model loading

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: destroy deferred GPU buffers on teardown

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: preserve deferred cleanup semantics

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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.

1 participant