Make GPU tools run to completion - #37
Merged
Merged
Conversation
In the 0.6.0 manual test the model started a ComfyUI workflow with wait: false. The GPU hand-off then didn't hold: lcode's model reloaded for the next step while ComfyUI was still generating, and they competed for the GPU (it happened to finish in time). For tools marked free_gpu that take a boolean `wait`, lcode now always sends wait: true. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Found in the 0.6.0 manual test.
The problem: the model started a ComfyUI workflow with
run_workflow(wait: false), then polled withjob. The GPU hand-off didn't hold: lcode's model reloaded for the next step while ComfyUI was still generating, so they competed for the 12 GB GPU. This time ComfyUI happened to finish during the reload.The fix: for tools marked
free_gputhat take a booleanwait, lcode now always sendswait: true. The job finishes before lcode's model comes back.test_gpu_tools_run_to_completion.The rest of the 0.6.0 manual test passed, with the PyPI build:
doctorshows the vision model.lcode mcp add comfyuiconnected (17 tools,free_gpuset).🤖 Generated with Claude Code