Skip to content

[ModelRunner] Refactor model_runner for NPU #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wangxiyuan merged 2 commits into from
Feb 6, 2025
Merged

[ModelRunner] Refactor model_runner for NPU #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8b45b23
This PR is a refactoring of model runner, to decouple it from the cla…
shen-shanshan Feb 5, 2025
ee70750
update
shen-shanshan Feb 5, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,3 +192,4 @@ cython_debug/
# PyPI configuration file
.pypirc

kernel_meta/
6 changes: 6 additions & 0 deletions vllm_ascend/attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -321,6 +321,12 @@ class AscendMetadataBuilder(CommonMetadataBuilder[AscendMetadata]):

_metadata_cls = AscendMetadata

def __init__(self, input_builder: "ModelInputForNPUBuilder"):
self.input_builder = input_builder
self.runner = input_builder.runner
self.sliding_window = input_builder.sliding_window
self.block_size = input_builder.block_size

def compute_npu_slot_indices(self, is_profile_run, slot_indices, seq_id,
seq_len, context_len, start_idx, block_size,
block_tables, max_query_len):
Expand Down
Loading