feat: support beam search kernel for decode-only model. #269
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
yjw258
force-pushed
the
features/beam_search_npu
branch
from
8303520 to
3ef9f6b
Compare
RobbieLeung
reviewed
Oct 23, 2025
| torch::cat({batched_fwd_inputs.acc_logprob, | ||
| batched_fwd_inputs.micro_inputs[i].acc_logprob}, | ||
| -1); | ||
| } |
Collaborator
There was a problem hiding this comment.
Consider using std::vector<torch::Tensor> acc_logprob_vec; and torch::stack(acc_logprob_vec); for better performance.
xllm/core/runtime/worker_impl.h
Outdated
|
|
||
| std::unique_ptr<Sampler> sampler_; | ||
|
|
||
| std::unique_ptr<BeamSearcher> beam_searcher_; |
Collaborator
There was a problem hiding this comment.
Move it to LLMWorkerImpl since beam searcher is only worked for llm.
yjw258
force-pushed
the
features/beam_search_npu
branch
from
3ef9f6b to
f9654c4
Compare
liutongxuan
approved these changes
Oct 24, 2025
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Outdated suggestions cannot be applied.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.
Use beam search kernel to select candidates in beam search kernel, and add a launch parameter
enable_beam_search_kernelto control this behavior.Performance Results