feat: multi-agent swarm with live dashboard and auto-reporting#130
Draft
rock-mind wants to merge 1 commit intokarpathy:masterfrom
Draft
feat: multi-agent swarm with live dashboard and auto-reporting#130rock-mind wants to merge 1 commit intokarpathy:masterfrom
rock-mind wants to merge 1 commit intokarpathy:masterfrom
Conversation
|
Thanks for the PR! Could you add a description of what changes you've made and why? |
Add swarm.py (~130 lines) that creates isolated git worktrees so multiple agents can run experiments in parallel on different GPUs. - Each agent gets its own worktree, branch, and train.py copy - Optional --baseline flag to run baseline on all agents at once - No new dependencies, no changes to existing files - Cleanup with --cleanup Usage: uv run swarm.py --tag mar10 --gpus 0,1,2,3
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add
swarm.py(~130 lines), a multi-GPU launcher that creates isolated git worktrees so multiple agents can run experiments in parallel.Why
The README mentions adding more agents. With multiple GPUs, you can run N agents simultaneously — each on its own GPU, branch, and copy of
train.py. 4 GPUs = ~400 experiments overnight instead of ~100.What changed
New file:
swarm.py(129 lines, no new dependencies)Creates isolated git worktrees per agent, optionally runs baselines in parallel, then prints instructions for opening Claude Code / Codex in each worktree.
Modified:
README.md(+14 lines)Added a short "Multi-GPU" section documenting
swarm.pyusage, and one line in the project structure list.No changes to
prepare.py,train.py,program.md, orpyproject.toml.