Skip to content

[Bugfix] Fix broken CI #1848

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
merged 3 commits into from
Jul 17, 2025
Merged

[Bugfix] Fix broken CI #1848

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
251ca09
fix bug
Potabk Jul 17, 2025
e0db676
fix
Potabk Jul 17, 2025
ea366e5
fix spec decode
Potabk Jul 17, 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
16 changes: 0 additions & 16 deletions vllm_ascend/pool/__init__.py
View file
Open in desktop

This file was deleted.

32 changes: 0 additions & 32 deletions vllm_ascend/pool/metadata.py
View file
Open in desktop

This file was deleted.

12 changes: 9 additions & 3 deletions vllm_ascend/worker/model_runner_v1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@
KVCacheSpec)
from vllm.v1.outputs import (EMPTY_MODEL_RUNNER_OUTPUT, LogprobsTensors,
ModelRunnerOutput)
from vllm.v1.pool.metadata import PoolingMetadata
from vllm.v1.sample.metadata import SamplingMetadata
from vllm.v1.sample.sampler import Sampler
from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
Expand All @@ -76,7 +77,6 @@
from vllm_ascend.attention.mla_v1 import (AscendMLAMetadata,
CommonAttentionMetadata)
from vllm_ascend.platform import NPUPlatform
from vllm_ascend.pool.metadata import PoolingMetadata
from vllm_ascend.sample.rejection_sampler import AscendRejectionSampler
from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_ND, ACL_FORMAT_FRACTAL_NZ,
ProfileExecuteDuration,
Expand Down Expand Up @@ -571,7 +571,10 @@ def get_eagle_atten_dict(

# OPTIMIZATION: Start copying the block table first.
# This way, we can overlap the copy with the following CPU operations.
self.input_batch.block_table.commit(num_reqs)
if vllm_version_is("0.9.2"):
self.input_batch.block_table.commit(num_reqs)
else:
self.input_batch.block_table.commit_block_table(num_reqs)

# Get the number of scheduled tokens for each request.
req_ids = self.input_batch.req_ids
Expand Down Expand Up @@ -902,7 +905,10 @@ def _process_reqs(

# OPTIMIZATION: Start copying the block table first.
# This way, we can overlap the copy with the following CPU operations.
self.input_batch.block_table.commit(num_reqs)
if vllm_version_is("0.9.2"):
self.input_batch.block_table.commit(num_reqs)
else:
self.input_batch.block_table.commit_block_table(num_reqs)

# Get the number of scheduled tokens for each request.
# TODO: The Python loop can be slow. Optimize.
Expand Down
3 changes: 1 addition & 2 deletions vllm_ascend/worker/npu_input_batch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,14 +28,13 @@
from vllm.sampling_params import SamplingParams, SamplingType
from vllm.utils import swap_dict_values
from vllm.v1.outputs import LogprobsTensors
from vllm.v1.pool.metadata import PoolingMetadata
from vllm.v1.sample.logits_processor import init_builtin_logitsprocs
from vllm.v1.sample.metadata import SamplingMetadata
from vllm.v1.spec_decode.utils import is_spec_decode_unsupported
from vllm.v1.utils import copy_slice
from vllm.v1.worker.block_table import MultiGroupBlockTable

from vllm_ascend.pool.metadata import PoolingMetadata

_SAMPLING_EPS = 1e-5


Expand Down
Loading