EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Main2Main] Upgrade vllm commit to 0109 (#5752)

Browse Source 
### What this PR does / why we need it?
Upgrade vllm commit to 0109 (bde38c11df0ea066a740efe9b77fff5418be45df)

1. remove `init_cached_hf_modules ` due to
https://github.com/vllm-project/vllm/pull/31786
2. fix spec_decode e2e test due to
https://github.com/vllm-project/vllm/pull/29821 break
3. fix `vllm.v1.attention.backends.utils` duo to
https://github.com/vllm-project/vllm/pull/31891
4. fix `self.seq_lens - query_lens` on same device due to
https://github.com/vllm-project/vllm/pull/31773
5. skip model_runner_v2 e2e test due to `'_OpNamespace' '_C' object has
no attribute 'get_cuda_view_from_cpu_tensor'`

- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad
2026-01-13 19:14:43 +08:00
committed by GitHub
parent eed9e366a7
commit f7b904641e
21 changed files with 203 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
tests/ut/worker/test_worker_v1.py
View File

@@ -5,6 +5,7 @@ import torch
from vllm.config import CacheConfig, ModelConfig, ParallelConfig, VllmConfig
from tests.ut.base import TestBase
from vllm_ascend.utils import vllm_version_is
init_cached_hf_modules_path = "vllm.utils.import_utils.init_cached_hf_modules"
@@ -52,7 +53,7 @@ class TestNPUWorker(TestBase):
@patch("vllm_ascend.worker.worker.get_ascend_config")
@patch("vllm_ascend.worker.worker.init_ascend_config")
@patch("vllm_ascend.worker.worker.check_ascend_device_type")
@patch(init_cached_hf_modules_path)
@patch(init_cached_hf_modules_path, create=True)
@patch("vllm_ascend.worker.worker.NPUWorker._init_profiler")
def test_init_npu_worker_normal_case(
self,
@@ -106,7 +107,7 @@ class TestNPUWorker(TestBase):
@patch("vllm_ascend.worker.worker.get_ascend_config")
@patch("vllm_ascend.worker.worker.init_ascend_config")
@patch("vllm_ascend.worker.worker.check_ascend_device_type")
@patch(init_cached_hf_modules_path)
@patch(init_cached_hf_modules_path, create=True)
@patch("vllm_ascend.worker.worker.NPUWorker._init_profiler")
def test_init_npu_worker_with_trust_remote_code(
self,
@@ -140,7 +141,10 @@ class TestNPUWorker(TestBase):
)
# Verify init_cached_hf_modules is called (trust_remote_code=True)
mock_init_cached_hf_modules.assert_called_once()
if vllm_version_is('0.13.0'):
mock_init_cached_hf_modules.assert_called_once()
else:
mock_init_cached_hf_modules.assert_not_called()
@patch("vllm_ascend.utils.adapt_patch")
@patch("vllm_ascend.ops")
@@ -149,7 +153,7 @@ class TestNPUWorker(TestBase):
@patch("vllm_ascend.worker.worker.get_ascend_config")
@patch("vllm_ascend.worker.worker.init_ascend_config")
@patch("vllm_ascend.worker.worker.check_ascend_device_type")
@patch(init_cached_hf_modules_path)
@patch(init_cached_hf_modules_path, create=True)
@patch("vllm_ascend.worker.worker.NPUWorker._init_profiler")
def test_init_npu_worker_with_custom_cache_dtype(
self,
@@ -813,10 +817,11 @@ class TestNPUWorker(TestBase):
mock_scheduler_output, None)
self.assertEqual(result, mock_model_output)
@patch("vllm_ascend.worker.worker.enable_sp", return_value=False)
@patch("vllm_ascend.worker.worker.get_pp_group")
@patch("vllm_ascend.worker.worker.get_tp_group")
def test_execute_model_middle_rank(self, mock_get_tp_group,
mock_get_pp_group):
mock_get_pp_group, mock_enable_sp):
"""Test execute_model method - middle rank case"""
from vllm.sequence import IntermediateTensors
@@ -1113,12 +1118,14 @@ class TestNPUWorker(TestBase):
worker.model_runner.initialize_kv_cache.assert_called_once_with(
mock_kv_cache_config)
@patch("vllm_ascend.worker.worker.enable_sp", return_value=False)
@patch("vllm_ascend.worker.worker.get_pp_group")
@patch("vllm_ascend.worker.worker.get_tp_group")
@patch("vllm_ascend.worker.worker.EMPTY_MODEL_RUNNER_OUTPUT")
def test_execute_model_kv_connector_not_finished(self, mock_empty_output,
mock_get_tp_group,
mock_get_pp_group):
mock_get_pp_group,
mock_enable_sp):
"""Test execute_model method - kv_connector_output not finished sending/recving case"""
from vllm.sequence import IntermediateTensors