Skip to content

feat: promote fully_async rollout into core (slime #1920) #116

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.

Sign up for GitHub

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
CalvinXKY merged 1 commit into from
Jun 2, 2026
Merged

feat: promote fully_async rollout into core (slime #1920) #116

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/pr-test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ jobs:
strategy:
fail-fast: false
matrix:
info: [{"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_async_short.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_short.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_ppo_critic_only_short.py"}]
info: [{"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_async_short.py"}, {"num_gpus": 4, "test_file": "test_qwen3.5_0.8B_gsm8k_short.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_ppo_critic_only_short.py"}, {"num_gpus": 4, "test_file": "test_qwen2.5_0.5B_fully_async_short.py"}]
defaults:
run:
working-directory: ${{ github.workspace }}
Expand Down
1 change: 1 addition & 0 deletions .github/workflows/pr-test.yml.j2
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
{'test_file': 'test_qwen3.5_0.8B_gsm8k_async_short.py', 'num_gpus': 4},
{'test_file': 'test_qwen3.5_0.8B_gsm8k_short.py', 'num_gpus': 4},
{'test_file': 'test_qwen2.5_0.5B_ppo_critic_only_short.py', 'num_gpus': 4},
{'test_file': 'test_qwen2.5_0.5B_fully_async_short.py', 'num_gpus': 4},
],
},
'e2e-test-vllm-config': {
Expand Down
5 changes: 3 additions & 2 deletions examples/fully_async/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,8 @@
This example shows a simple way to make rollout generation **fully asynchronous**: a single global worker is created once and then keeps running in the background, continuously pulling prompts and launching generation tasks. Training only needs to fetch already finished results. This removes the per‑step wait that happens in the normal synchronous style.

## Files
* `fully_async_rollout.py`: global async worker + `generate_rollout_fully_async` entry.
The fully-async worker has been **promoted from this example into the core package** — it now lives in
`vime/rollout/fully_async_rollout.py`. This directory keeps only the launch script:
* `run-qwen3-4b-fully_async.sh`: example launch script with Qwen3‑4B.

## Prerequisite
Expand Down Expand Up @@ -37,7 +38,7 @@ To enable the fully async pattern there are only two changes compared to a norma
1. Use the async training driver: `train_async.py` (not `train.py`).
2. Set the rollout function path:
```bash
--rollout-function-path fully_async_rollout.generate_rollout_fully_async
--rollout-function-path vime.rollout.fully_async_rollout.generate_rollout_fully_async
```

Why is it still "fully" async although `train_async.py` itself schedules rollouts step‑by‑step?
Expand Down
262 changes: 0 additions & 262 deletions examples/fully_async/fully_async_rollout.py
View file
Open in desktop

This file was deleted.

2 changes: 1 addition & 1 deletion examples/fully_async/run-qwen3-4b-fully_async.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ CKPT_ARGS=(
PROMPT_SET=/path/to/dapo-math-17k.jsonl

ROLLOUT_ARGS=(
--rollout-function-path fully_async_rollout.generate_rollout_fully_async
--rollout-function-path vime.rollout.fully_async_rollout.generate_rollout_fully_async
--prompt-data ${PROMPT_SET}
--input-key prompt
--label-key label
Expand Down
Loading