Move fully_async example to main codebase - #1920
Merged
Merged
Conversation
zhuzilin
force-pushed
the
zilin/fully-async
branch
from
May 18, 2026 11:30
5d33f01 to
c27e802
Compare
CalvinXKY
pushed a commit
to vllm-project/vime
that referenced
this pull request
Jun 2, 2026
Port of THUDM/slime#1920 — moves the fully-async rollout from an example into the core package so it's usable via --rollout-function-path vime.rollout.fully_async_rollout.generate_rollout_fully_async. - vime/rollout/fully_async_rollout.py (new): promoted from examples/fully_async/fully_async_rollout.py and translated to vime's vLLM seam (vime.rollout.vllm_rollout, args.vllm_server_concurrency). Carries slime's promotion refinements: docstring, logging, __all__, atexit cleanup, num_engines concurrency scaling, ABORTED->data_buffer redirect, fan-out handling. - vime/rollout/vllm_rollout.py: generate_and_rm_group return type -> list[Sample] | list[list[Sample]] + comment (analog of slime's sglang_rollout change; supports --custom-generate-function-path fan-out into multiple samples). - examples/fully_async/: remove the now-duplicated fully_async_rollout.py (moved to core); repoint run-qwen3-4b-fully_async.sh + README at the core --rollout-function-path. (vime keeps the 4B example rather than swapping to 0.5B as upstream did; the CI test below covers 0.5B.) - tests/test_qwen2.5_0.5B_fully_async_short.py (new) + registered in the run-ci-short matrix (pr-test.yml + .j2 regenerated). Mirrors test_qwen2.5_0.5B_async_short, only flipping the rollout-function-path. Refs: THUDM/slime#1920, #107 Signed-off-by: aoshen02 <aoshen@inferact.ai> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
momo609
pushed a commit
to vllm-project/vime
that referenced
this pull request
Jun 8, 2026
Port of THUDM/slime#1920 — moves the fully-async rollout from an example into the core package so it's usable via --rollout-function-path vime.rollout.fully_async_rollout.generate_rollout_fully_async. - vime/rollout/fully_async_rollout.py (new): promoted from examples/fully_async/fully_async_rollout.py and translated to vime's vLLM seam (vime.rollout.vllm_rollout, args.vllm_server_concurrency). Carries slime's promotion refinements: docstring, logging, __all__, atexit cleanup, num_engines concurrency scaling, ABORTED->data_buffer redirect, fan-out handling. - vime/rollout/vllm_rollout.py: generate_and_rm_group return type -> list[Sample] | list[list[Sample]] + comment (analog of slime's sglang_rollout change; supports --custom-generate-function-path fan-out into multiple samples). - examples/fully_async/: remove the now-duplicated fully_async_rollout.py (moved to core); repoint run-qwen3-4b-fully_async.sh + README at the core --rollout-function-path. (vime keeps the 4B example rather than swapping to 0.5B as upstream did; the CI test below covers 0.5B.) - tests/test_qwen2.5_0.5B_fully_async_short.py (new) + registered in the run-ci-short matrix (pr-test.yml + .j2 regenerated). Mirrors test_qwen2.5_0.5B_async_short, only flipping the rollout-function-path. Refs: THUDM/slime#1920, #107 Signed-off-by: aoshen02 <aoshen@inferact.ai> Co-authored-by: Claude Opus 4.8 (1M context) <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.
No description provided.