[Chore] Minor simplification for non-PP path #24810
Merged
Conversation
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
Signed-off-by: Woosuk Kwon <[email protected]>
WoosukKwon
requested review from
robertgshaw2-redhat,
njhill,
ywang96,
comaniac and
alexm-redhat
as code owners
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request provides a nice simplification to the execute_model method in GPUModelRunner. By moving the broadcast_pp_output flag to the __init__ method and restructuring the logic to handle the common (non-broadcast) and rare (broadcast) paths separately, the code becomes much clearer and easier to follow. This refactoring also correctly handles kv_connector_output for pooling models and appears to fix a latent bug where logits were not updated on non-last pipeline parallel ranks after being broadcast. The changes are well-contained and improve both readability and correctness. I have no further suggestions.
njhill
approved these changes
Sep 13, 2025
| model_output_broadcast_data = { | ||
| "logits": logits.contiguous(), | ||
| } if logits is not None else {} | ||
| else: |
There was a problem hiding this comment.
just a thought, could we put the else logic in a different function to be even less intrusive to the common path?
BoyuanFeng
pushed a commit
to BoyuanFeng/vllm
that referenced
this pull request
Sep 14, 2025
Signed-off-by: Woosuk Kwon <[email protected]>
845473182
pushed a commit
to dsxsteven/vllm_splitPR
that referenced
this pull request
Sep 15, 2025
…to loader * 'loader' of https://github.com/dsxsteven/vllm_splitPR: (123 commits) [Hybrid Allocator] Support Pipeline Parallel (vllm-project#23974) [Spec Decoding]Support Spec Decoding Metrics in DP Mode (vllm-project#24049) [Chore] Remove ipex_ops warning (vllm-project#24835) Force use C++17 globally to avoid compilation error (vllm-project#24823) [Benchmarks] Throw usage error when using dataset-name random and dataset-path together (vllm-project#24819) fix type of sampling rate for encode_base64 (vllm-project#24826) [Perf] Fix DeepGEMM Contiguous Layout Issue, 5.5% Throughput Improvement (vllm-project#24783) [Misc] Improve `s3_utils` type hints with `BaseClient` (vllm-project#24825) [Multi Modal][Performance] Fused Q,K's apply_rope into one (vllm-project#24511) [Chore] Minor simplification for non-PP path (vllm-project#24810) [Minor] Simplify duplicative device check for cuda (vllm-project#24793) Remove redundant assignment in xfer_buffers, This is a little fix (vllm-project#24732) [CI][Spec Decode] Adjust threshold for flaky ngram spec decoding test again (vllm-project#24771) [Doc]: fix typos in various files (vllm-project#24798) [Misc] Correct an outdated comment. (vllm-project#24765) [CI Failure] Fix test_flashinfer_cutlass_mxfp4_mxfp8_fused_moe (vllm-project#24750) [Core][Multimodal] Cache `supports_kw` (vllm-project#24773) [Kernels][DP/EP] Optimize Silu Kernel for R1 (vllm-project#24054) [Perf] Use NVIDIA hardware-accelerated instruction for float to fp8_e4m3 quantization (vllm-project#24757) [Doc]: Remove 404 hyperlinks (vllm-project#24785) ...
dsxsteven
pushed a commit
to dsxsteven/vllm_splitPR
that referenced
this pull request
Sep 15, 2025
Signed-off-by: Woosuk Kwon <[email protected]>
bbartels
pushed a commit
to bbartels/vllm
that referenced
this pull request
Sep 15, 2025
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: bbartels <[email protected]>
cboss6
pushed a commit
to cboss6/vllm
that referenced
this pull request
Sep 16, 2025
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: bruceszchen <[email protected]>
cboss6
pushed a commit
to cboss6/vllm
that referenced
this pull request
Sep 16, 2025
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: bruceszchen <[email protected]>
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.
Currently,
broadcast_pp_outputcomplicates the logic in the common non-PP path.This PR simplifies the logic a bit.