[perf] optimize apply_penalties & topKtopP for V0&V1 Engine #1107
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: linfeng-yuan <1102311262@qq.com>
linfeng-yuan
force-pushed
the
sampler_optimization
branch
from
83094bb to
f7d8c2b
Compare
MengqingCao
reviewed
Jun 6, 2025
| from vllm.v1.sample.ops.topk_topp_sampler import TopKTopPSampler, random_sample | ||
|
|
||
|
|
||
| class AscendTopKTopPSampler(TopKTopPSampler): |
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
What this PR does / why we need it?
Same as pull/525, this PR optimizes apply_penalties & topKtopP implementation in both V0/V1 Engine by avoiding using torch.scatter and matrix indexing operations.
Does this PR introduce any user-facing change?
No.
How was this patch tested?
This patch was tested with vllm v0.9.0, torch-2.5.1 & torch_npu-2.5.1 (both torch_npu in PyPI and newest internal beta version). At a concurrency of 58 and with post-processing parameters set to "temperature": 0.2, "top_k": 1000, "top_p": 0.92, the average sampling time in each decoding stage was reduced from 90ms to 8ms.