Skip to content

refactor: split sync/async vllm worker ([1/2] of refactor vllm worker) #900

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

Jump to bottom
Merged
parthchadha merged 6 commits into from
Aug 14, 2025
Merged

refactor: split sync/async vllm worker ([1/2] of refactor vllm worker) #900

parthchadha merged 6 commits into from
Aug 14, 2025

Conversation

@yuki-97
Copy link
Contributor

@yuki-97 yuki-97 commented Aug 12, 2025 •
edited
Loading

What does this PR do ?

step 1 of refactor vllm worker:

  1. put vllm stuffs from nemo_rl/models/generation to nemo_rl/models/generation/vllm, so that it's easy for us to support other inference FW in the future.
  2. split sync and async vllm worker to different files to make it clear.

Test Result

convergence time 
FSDP2 with sync vllm
 image image 
Megatron with async vllm
 image image

Issues

Related #599.

@yuki-97 yuki-97 changed the title refactor: move files and split sync/async vllm worker ([1/2] of refactor vllm worker) refactor: split sync/async vllm worker ([1/2] of refactor vllm worker) Aug 12, 2025
@yuki-97 yuki-97 force-pushed the yukih/refactor-vllm-step-1 branch 2 times, most recently from c32df49 to 6041a5b Compare August 12, 2025 16:08
@yuki-97 yuki-97 added the CI:L1 Run doctests, unit tests, and functional tests label Aug 12, 2025
@github-actions github-actions bot added the documentation Improvements or additions to documentation label Aug 13, 2025
@yuki-97 yuki-97 force-pushed the yukih/refactor-vllm-step-1 branch from 01d2f21 to c09ddad Compare August 13, 2025 03:33
@yuki-97 yuki-97 added CI:docs Run doctest and removed CI:L1 Run doctests, unit tests, and functional tests labels Aug 13, 2025
@yuki-97 yuki-97 marked this pull request as ready for review August 13, 2025 03:52
terrykong
terrykong reviewed Aug 13, 2025
View reviewed changes
yuki-97 added 6 commits August 14, 2025 21:34
@yuki-97
move files
b55f541 
Signed-off-by: Yuki Huang <[email protected]>
@yuki-97
remove duplicated code
73ee68c 
Signed-off-by: Yuki Huang <[email protected]>
@yuki-97
lint
c7c47ff 
Signed-off-by: Yuki Huang <[email protected]>
@yuki-97
fix path
51db8c2 
Signed-off-by: Yuki Huang <[email protected]>
@yuki-97
fix doc
8d0d7eb 
Signed-off-by: Yuki Huang <[email protected]>
@yuki-97
use absolute import
7cb2463 
Signed-off-by: Yuki Huang <[email protected]>
@yuki-97 yuki-97 force-pushed the yukih/refactor-vllm-step-1 branch from 3a2a649 to 7cb2463 Compare August 14, 2025 13:34
@parthchadha parthchadha added this pull request to the merge queue Aug 14, 2025
Merged via the queue into main with commit 83c6bfc Aug 14, 2025
19 checks passed
@parthchadha parthchadha deleted the yukih/refactor-vllm-step-1 branch August 14, 2025 16:53
zhandaz pushed a commit that referenced this pull request Aug 19, 2025
@yuki-97 @zhandaz
refactor: split sync/async vllm worker ([1/2] of refactor vllm worker) (
8f05264 
#900)

Signed-off-by: Yuki Huang <[email protected]>
youngeunkwon0405 added a commit to youngeunkwon0405/RL that referenced this pull request Aug 25, 2025
@youngeunkwon0405
Squashed commit of the following:
c3d6c43 
commit b246e55
Author: Youngeun Kwon <[email protected]>
Date:   Mon Aug 25 15:05:48 2025 -0700

    update the script

    Signed-off-by: Youngeun Kwon <[email protected]>

commit 5315a6b
Author: Youngeun Kwon <[email protected]>
Date:   Mon Aug 25 13:59:16 2025 -0700

    script update

    Signed-off-by: Youngeun Kwon <[email protected]>

commit 4437402
Author: Youngeun Kwon <[email protected]>
Date:   Tue Jul 15 17:42:23 2025 -0700

    local

    Signed-off-by: Youngeun Kwon <[email protected]>

    wip

    Signed-off-by: Youngeun Kwon <[email protected]>

    add script

    Signed-off-by: Youngeun Kwon <[email protected]>

    update script

    Signed-off-by: Youngeun Kwon <[email protected]>

    update script

    Signed-off-by: Youngeun Kwon <[email protected]>

    interactive

    Signed-off-by: Youngeun Kwon <[email protected]>

commit b721703
Author: Charlie Truong <[email protected]>
Date:   Mon Aug 18 11:22:54 2025 -0500

    build: Fix pytorch image ref in Dockerfile.ngc_pytorch (NVIDIA-NeMo#936)

    Signed-off-by: Charlie Truong <[email protected]>

commit 70b9666
Author: Charlie Truong <[email protected]>
Date:   Sun Aug 17 21:17:58 2025 -0500

    build: Add Dockerfile that uses NGC pytorch image (NVIDIA-NeMo#897)

    Signed-off-by: Charlie Truong <[email protected]>

commit df31c1b
Author: pjin-nvidia <[email protected]>
Date:   Thu Aug 14 18:34:50 2025 -0700

    feat: chunked logprob calculation with deferred fp32 cast to help with OOM (NVIDIA-NeMo#918)

    Signed-off-by: Peter Jin <[email protected]>

commit 83c6bfc
Author: yuki <[email protected]>
Date:   Thu Aug 14 21:48:55 2025 +0800

    refactor: split sync/async vllm worker ([1/2] of refactor vllm worker) (NVIDIA-NeMo#900)

    Signed-off-by: Yuki Huang <[email protected]>

commit 9f7825e
Author: Rayen <[email protected]>
Date:   Thu Aug 14 12:38:27 2025 +0800

    feat: Add TP to embed_tokens and lm_head for Gemma models (NVIDIA-NeMo#879)

    Signed-off-by: ruit <[email protected]>

commit e1f56c4
Author: Terry Kong <[email protected]>
Date:   Tue Aug 12 13:09:37 2025 -0700

    feat: add diagnostic script for problematic embeddings (NVIDIA-NeMo#896)

    Signed-off-by: Terry Kong <[email protected]>

commit 223bfa8
Author: Gerald Shen <[email protected]>
Date:   Mon Aug 11 18:19:52 2025 -0700

    feat: add nemotron5 sharding (NVIDIA-NeMo#481)

    Signed-off-by: Terry Kong <[email protected]>
    Co-authored-by: Terry Kong <[email protected]>

commit 18b9e2c
Author: Terry Kong <[email protected]>
Date:   Mon Aug 11 15:08:52 2025 -0700

    test: lower step count on gemma nightly test to finish within 4 hours (NVIDIA-NeMo#880)

    Signed-off-by: Terry Kong <[email protected]>

commit 8fd8c96
Author: guyueh1 <[email protected]>
Date:   Mon Aug 11 10:46:29 2025 -0700

    feat: Fix and enhances for Nsight system profiling (NVIDIA-NeMo#865)

    Signed-off-by: Guyue Huang <[email protected]>

commit 2b87def
Author: Qidong Su <[email protected]>
Date:   Fri Aug 8 18:54:20 2025 -0400

    fix: OOM in deepscaler1.5b with sequence length = 16/24k  (NVIDIA-NeMo#875)

    Signed-off-by: Qidong Su <[email protected]>

commit fecf71e
Author: Rayen <[email protected]>
Date:   Sat Aug 9 06:42:07 2025 +0800

    fix: remove tie weight check (NVIDIA-NeMo#700)

    Signed-off-by: ruit <[email protected]>

commit d45ff3f
Author: Terry Kong <[email protected]>
Date:   Fri Aug 8 10:07:02 2025 -0700

    test: add deepscaler tests + pipe-clean configs + fix eval for deepscaler (NVIDIA-NeMo#866)

    Signed-off-by: Terry Kong <[email protected]>

commit d73c942
Author: Anna Shors <[email protected]>
Date:   Fri Aug 8 09:27:15 2025 -0700

    feat: qwen3 export to HF (NVIDIA-NeMo#873)

    Signed-off-by: Abdalgader Abubaker <[email protected]>
    Signed-off-by: Anna Shors <[email protected]>
    Co-authored-by: Abdalgader Abubaker <[email protected]>

commit e924d33
Author: Shang Wang <[email protected]>
Date:   Fri Aug 8 12:15:34 2025 -0400

    docs: Link uv's installation instructions to uv's website (NVIDIA-NeMo#837)

    Signed-off-by: Shang Wang <[email protected]>

commit bbbb3d6
Author: yuki <[email protected]>
Date:   Fri Aug 8 23:26:15 2025 +0800

    fix: fix non-colocated with cpu_offload enabled (NVIDIA-NeMo#861)

    Signed-off-by: Yuki Huang <[email protected]>

commit 88a399e
Author: yuki <[email protected]>
Date:   Fri Aug 8 14:04:08 2025 +0800

    chore: remove old fsdp1 unit test (NVIDIA-NeMo#871)

    Signed-off-by: Yuki Huang <[email protected]>

commit b8a89a9
Author: yuki <[email protected]>
Date:   Fri Aug 8 13:56:19 2025 +0800

    feat: support non-colocated in mcore (NVIDIA-NeMo#613)

    Signed-off-by: Yuki Huang <[email protected]>

commit 5910abb
Author: Anna Shors <[email protected]>
Date:   Thu Aug 7 13:11:43 2025 -0700

    feat: support DTensor CP in DPO and SFT (NVIDIA-NeMo#798)

    Signed-off-by: ashors1 <[email protected]>

commit 0988a7d
Author: Felipe Vieira Frujeri <[email protected]>
Date:   Wed Aug 6 22:01:32 2025 -0700

    fix: Fix error message in VllmGenerationWorker. (NVIDIA-NeMo#633)

    Signed-off-by: Felipe Vieira Frujeri <[email protected]>

commit 233cc07
Author: Parth Chadha <[email protected]>
Date:   Wed Aug 6 15:14:22 2025 -0700

    fix: force use of eager (disabled cuda graphs) due to convergence issues (NVIDIA-NeMo#857)

    Signed-off-by: Parth Chadha <[email protected]>

commit 0557402
Author: Terry Kong <[email protected]>
Date:   Wed Aug 6 14:44:29 2025 -0700

    chore: 0.3.0 -> 0.4.0rc0 (NVIDIA-NeMo#840)

    Signed-off-by: Terry Kong <[email protected]>

commit 03472a0
Author: Terry Kong <[email protected]>
Date:   Wed Aug 6 14:43:55 2025 -0700

    feat: dockerfile can build hermetically or from build context (NVIDIA-NeMo#799)

    Signed-off-by: Terry Kong <[email protected]>

commit 9af0a52
Author: Anna Shors <[email protected]>
Date:   Wed Aug 6 12:35:51 2025 -0700

    fix: fix grpo + mcore checkpointing without validation (NVIDIA-NeMo#844)

    Signed-off-by: ashors1 <[email protected]>

commit b6269f7
Author: Yubo Gao <[email protected]>
Date:   Tue Aug 5 16:55:02 2025 -0400

    feat: track policy training compute throughput (NVIDIA-NeMo#632)

    Signed-off-by: Yubo Gao <[email protected]>

commit b74c5d0
Author: Wei Du <[email protected]>
Date:   Tue Aug 5 15:05:13 2025 -0500

    feat: save checkpoint before timeout to avoid 4-hour runtime limit (NVIDIA-NeMo#734)

    Signed-off-by: Wei Du <[email protected]>
    Signed-off-by: Terry Kong <[email protected]>
    Co-authored-by: Terry Kong <[email protected]>

commit c784dd9
Author: Zhiyu Li <[email protected]>
Date:   Tue Aug 5 10:47:30 2025 -0700

    feat: add data shuffle and random seed option (NVIDIA-NeMo#334)

    Signed-off-by: Zhiyu Li <[email protected]>
    Signed-off-by: Zhiyu Li <[email protected]>

commit c249efc
Author: Abdalgader Abubaker <[email protected]>
Date:   Tue Aug 5 21:33:28 2025 +0400

    docs: fix checkpointing command for megatron->hf export  (NVIDIA-NeMo#823)

    Signed-off-by: abdalgader-a <[email protected]>

Signed-off-by: Youngeun Kwon <[email protected]>
jveronvialard pushed a commit that referenced this pull request Aug 27, 2025
@yuki-97 @jveronvialard
refactor: split sync/async vllm worker ([1/2] of refactor vllm worker) (
ba29d45 
#900)

Signed-off-by: Yuki Huang <[email protected]>
Signed-off-by: Julien Veron Vialard <[email protected]>
soodoshll pushed a commit to soodoshll/RL that referenced this pull request Sep 4, 2025
@yuki-97 @soodoshll
refactor: split sync/async vllm worker ([1/2] of refactor vllm worker) (
c13e168 
NVIDIA-NeMo#900)

Signed-off-by: Yuki Huang <[email protected]>
Signed-off-by: Qidong Su <[email protected]>
@yuki-97 yuki-97 mentioned this pull request Sep 17, 2025
Open
PrinsYin pushed a commit to PrinsYin/RL that referenced this pull request Nov 30, 2025
@yuki-97
refactor: split sync/async vllm worker ([1/2] of refactor vllm worker) (
6fa5436 
NVIDIA-NeMo#900)

Signed-off-by: Yuki Huang <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@guyueh1 guyueh1 guyueh1 left review comments

@terrykong terrykong terrykong approved these changes

@parthchadha parthchadha parthchadha approved these changes

Assignees

No one assigned

Labels

CI:docs Run doctest documentation Improvements or additions to documentation

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@yuki-97 @terrykong @parthchadha @guyueh1