8000 feat: support async in non-colocated by yuki-666 · Pull Request #523 · NVIDIA-NeMo/RL · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

feat: support async in non-colocated #523

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 27, 2025
Merged

Conversation

yuki-666
Copy link
Contributor
@yuki-666 yuki-666 commented Jun 17, 2025

Test Result

convergence generation time
image image

Issues

Closes #394
Closes #508

Usage

uv run python examples/run_grpo_math.py \
    policy.generation.colocated.enabled=false \
    policy.generation.colocated.resources.gpus_per_node=1 \
    policy.generation.vllm_cfg.async_engine=true \
    cluster.gpus_per_node=2 \
    cluster.num_nodes=1

@yuki-666 yuki-666 added the CI:L1 Run doctests, unit tests, and functional tests label Jun 17, 2025
@yuki-666 yuki-666 added CI:L1 Run doctests, unit tests, and functional tests and removed CI:L1 Run doctests, unit tests, and functional tests labels Jun 19, 2025
@yuki-666 yuki-666 force-pushed the yukih/non-colocated-async branch 2 times, most recently from 491bd44 to 0efc71c Compare June 26, 2025 10:24
@yuki-666 yuki-666 marked this pull request as ready for review June 26, 2025 10:57
@yuki-666 yuki-666 added CI:L1 Run doctests, unit tests, and functional tests and removed CI:L1 Run doctests, unit tests, and functional tests labels Jun 26, 2025
@yuki-666 yuki-666 force-pushed the yukih/non-colocated-async branch from 0efc71c to c187f3d Compare June 26, 2025 13:50
@yuki-666 yuki-666 added CI:L1 Run doctests, unit tests, and functional tests and removed CI:L1 Run doctests, unit tests, and functional tests labels Jun 26, 2025
yuki-666 added 2 commits June 26, 2025 14:08
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
@yuki-666 yuki-666 force-pushed the yukih/non-colocated-async branch from c187f3d to 48018a3 Compare June 26, 2025 14:09
@yuki-666 yuki-666 added CI:L1 Run doctests, unit tests, and functional tests and removed CI:L1 Run doctests, unit tests, and functional tests labels Jun 26, 2025
@terrykong terrykong added this pull request to the merge queue Jun 27, 2025
Merged via the queue into main with commit 7100f1d Jun 27, 2025
21 of 23 checks passed
@terrykong terrykong deleted the yukih/non-colocated-async branch June 27, 2025 22:13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CI:L1 Run doctests, unit tests, and functional tests
Projects
None yet
Development

Successfully merging this pull request may close these issues.

support async non-colocated vllm Add non-colocated refit
3 participants
0