fix ci

Signed-off-by: MengqingCao <[email protected]>

Author: MengqingCao

.github/workflows/vllm_ascend_test.yaml

@@ -40,8 +40,8 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  # lint:
-  #   uses: ./.github/workflows/pre-commit.yml
+  lint:
+    uses: ./.github/workflows/pre-commit.yml
 
   changes:
     runs-on: ubuntu-latest

tests/e2e/singlecard/sample/test_rejection_sampler.py

@@ -4,7 +4,7 @@
 import pytest
 import torch
 import torch.nn.functional as F
-from vllm.v1.sample.logits_processor import LogitsProcessorManager
+from vllm.v1.sample.logits_processor import LogitsProcessors
 from vllm.v1.sample.metadata import SamplingMetadata
 from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
 
@@ -66,7 +66,7 @@ def create_sampling_metadata(
                             output_token_ids=[],
                             allowed_token_ids_mask=None,
                             bad_words_token_ids={},
-                            logitsprocs=LogitsProcessorManager())
+                            logitsprocs=LogitsProcessors())
 
 
 ########################### Tests for Greedy Sampling ###################

vllm_ascend/worker/model_runner_v1.py

@@ -1074,8 +1074,8 @@ def _process_reqs(
             num_input_tokens)
         num_input_tokens += num_pad
 
-        modified_batch = self.attn_metadata_builder.reorder_batch(
-            self.input_batch, scheduler_output)
+        self.attn_metadata_builder.reorder_batch(self.input_batch,
+                                                 scheduler_output)
         # 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_block_table(num_reqs)