merged_prefill for V1 #1342
Merged
merged_prefill for V1 #1342
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
|
/run-gaudi-tests |
4 similar comments
|
/run-gaudi-tests |
|
/run-gaudi-tests |
|
/run-gaudi-tests |
|
/run-gaudi-tests |
Signed-off-by: Michal Adamczyk <[email protected]>
madamczyk-intel
force-pushed
the
dev/madamczyk/v1_merged_prefill
branch
from
d4933e9 to
c663fe6
Compare
Signed-off-by: Michal Adamczyk <[email protected]>
Signed-off-by: Michal Adamczyk <[email protected]>
|
/run-gaudi-tests |
Signed-off-by: Michal Adamczyk <[email protected]>
|
/run-gaudi-tests |
This comment was marked as outdated.
This comment was marked as outdated.
Sorry, something went wrong.
Signed-off-by: Michal Adamczyk <[email protected]>
…v1_merged_prefill Signed-off-by: Michal Adamczyk <[email protected]>
|
/run-gaudi-tests |
Signed-off-by: Michal Adamczyk <[email protected]>
…v1_merged_prefill
|
/run-gaudi-tests |
Signed-off-by: Michal Adamczyk <[email protected]>
|
/run-gaudi-tests |
Signed-off-by: Michal Adamczyk <[email protected]>
…v1_merged_prefill
|
/run-gaudi-tests |
…v1_merged_prefill Signed-off-by: Michal Adamczyk <[email protected]>
Signed-off-by: Michal Adamczyk <[email protected]>
…v1_merged_prefill
|
/run-gaudi-tests |
madamczyk-intel
requested review from
kzawora-intel,
michalkuligowski,
mgawarkiewicz-intel,
vivekgoe,
afierka-intel,
xuechendi,
jikunshang and
mswiniarsk
as code owners
mswiniarsk
requested changes
Jun 16, 2025
mswiniarsk
reviewed
Jun 16, 2025
Signed-off-by: Michal Adamczyk <[email protected]>
Signed-off-by: Michal Adamczyk <[email protected]>
|
/run-gaudi-tests |
There was a problem hiding this comment.
Pull Request Overview
This PR introduces experimental support for merged_prefill in V1 and refactors prompt batch creation in preparation for prompt_chunking work with APC support.
- Replaces environment variable usage with get_config().merged_prefill in the HPU model runner
- Updates prefill metadata function signatures and default parameters in HPU attention backend
- Updates the vllm-hpu-extension dependency and adds new Jenkins test configurations for merged prefill
Reviewed Changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| vllm/worker/hpu_model_runner.py | Updated to use get_config().merged_prefill instead of environment variables for merged prefill configuration |
| vllm/v1/attention/backends/hpu_attn.py | Refactored prefill metadata functions to remove now-ignored parameters and to update their API for HPU V1 |
| requirements/hpu.txt | Updated commit pointer for vllm-hpu-extension dependency |
| .jenkins/test_config.yaml | Added new test jobs for merged prefill functionality |
mswiniarsk
approved these changes
Jun 17, 2025
|
/run-gaudi-tests |
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.
Notable changes [V1]:
extension PR: HabanaAI/vllm-hpu-extension#226