From adf4a9ce79b6d1ee9bec20f46d46bd8eec2318f8 Mon Sep 17 00:00:00 2001
From: shen-shanshan <467638484@qq.com>
Date: Thu, 29 May 2025 11:44:21 +0000
Subject: [PATCH] remove metrics patch

Signed-off-by: shen-shanshan <467638484@qq.com>
---
 .../patch/worker/patch_common/__init__.py     |  1 -
 .../worker/patch_common/patch_metrics.py      | 53 -------------------
 2 files changed, 54 deletions(-)
 delete mode 100644 vllm_ascend/patch/worker/patch_common/patch_metrics.py

diff --git a/vllm_ascend/patch/worker/patch_common/__init__.py b/vllm_ascend/patch/worker/patch_common/__init__.py
index 7618823ba6..08a4b608e4 100644
--- a/vllm_ascend/patch/worker/patch_common/__init__.py
+++ b/vllm_ascend/patch/worker/patch_common/__init__.py
@@ -20,7 +20,6 @@
 import vllm_ascend.patch.worker.patch_common.patch_utils  # noqa isort:skip
 import vllm_ascend.patch.worker.patch_common.patch_distributed  # noqa
 import vllm_ascend.patch.worker.patch_common.patch_eagle  # noqa
-import vllm_ascend.patch.worker.patch_common.patch_metrics  # noqa
 import vllm_ascend.patch.worker.patch_common.patch_minicpm  # noqa
 import vllm_ascend.patch.worker.patch_common.patch_multi_step_worker  # noqa
 import vllm_ascend.patch.worker.patch_common.patch_sampler  # noqa
diff --git a/vllm_ascend/patch/worker/patch_common/patch_metrics.py b/vllm_ascend/patch/worker/patch_common/patch_metrics.py
deleted file mode 100644
index 6d1f2dc0a9..0000000000
--- a/vllm_ascend/patch/worker/patch_common/patch_metrics.py
+++ /dev/null
@@ -1,53 +0,0 @@
-#
-# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
-# This file is a part of the vllm-ascend project.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-from typing import Callable
-
-import torch
-from vllm.spec_decode.metrics import AsyncMetricsCollector
-
-Timer = Callable[[], float]
-
-
-def _copy_rejsample_metrics_async(self) -> torch.npu.Event:
-    """
-    TODO: torch.cuda.xxx --> torch.npu.xxx
-    Copy rejection/typical-acceptance sampling metrics
-    (number of accepted tokens, etc) to CPU asynchronously.
-
-    Returns a NPU event recording when the copy is complete.
-    """
-    assert self._copy_stream is not None
-    self._copy_stream.wait_stream(torch.npu.current_stream())
-
-    with torch.npu.stream(self._copy_stream):
-        self._aggregate_num_accepted_tokens.copy_(
-            self.spec_decode_sampler.num_accepted_tokens, non_blocking=True)
-        self._aggregate_num_emitted_tokens.copy_(
-            self.spec_decode_sampler.num_emitted_tokens, non_blocking=True)
-        # Number of draft tokens is calculated on CPU, so no copy is
-        # required.
-        self._aggregate_num_draft_tokens = (
-            self.spec_decode_sampler.num_draft_tokens)
-
-    aggregate_metrics_ready = torch.npu.Event()
-    aggregate_metrics_ready.record(self._copy_stream)
-
-    return aggregate_metrics_ready
-
-
-AsyncMetricsCollector._copy_rejsample_metrics_async = _copy_rejsample_metrics_async