[DeepSeek R1] P/D chunked prefill warmup with chunk size using context blocks #2139
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
jerrychenhf
requested review from
afierka-intel,
kzawora-intel,
mgawarkiewicz,
michalkuligowski and
vivekgoe
as code owners
hlin99
approved these changes
Nov 20, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
Implement warmup for P/D chunked prefill when prefill chunk size is specified. This is a simpler warmup case for chunked prefill. When chunk size is not specified, the number of warmup cases will be increased by times of(max_seq_len / block_size) which is not realistic to implement.
This implement using the max_model_len and the chunk size to calculate the possible number of context chunks and warmup with this context chunks.