[Main2Main] Upgrade vllm commit to 0109 (#5752)
### 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:
@@ -78,6 +78,12 @@ class TestAscendRotaryEmbedding(unittest.TestCase):
|
||||
|
||||
def setUp(self):
|
||||
# Common setup for tests
|
||||
self.config_patcher = patch('vllm.config.vllm.get_current_vllm_config')
|
||||
self.mock_get_config = self.config_patcher.start()
|
||||
mock_config = MagicMock()
|
||||
mock_config.compilation_config.custom_ops = ["all"]
|
||||
|
||||
self.mock_get_config.return_value = mock_config
|
||||
self.positions = torch.tensor([1, 2, 3])
|
||||
self.query = torch.randn(3, 1, 32, dtype=torch.float16)
|
||||
self.key = torch.randn(3, 1, 32, dtype=torch.float16)
|
||||
@@ -242,6 +248,12 @@ class TestAscendDeepseekScalingRotaryEmbedding(TestBase):
|
||||
|
||||
def setUp(self):
|
||||
# Common setup for tests
|
||||
self.config_patcher = patch('vllm.config.vllm.get_current_vllm_config')
|
||||
self.mock_get_config = self.config_patcher.start()
|
||||
mock_config = MagicMock()
|
||||
mock_config.compilation_config.custom_ops = ["all"]
|
||||
|
||||
self.mock_get_config.return_value = mock_config
|
||||
self.positions = torch.tensor([1, 2, 3])
|
||||
self.query = torch.randn(3, 1, 32, dtype=torch.float16)
|
||||
self.key = torch.randn(3, 1, 32, dtype=torch.float16)
|
||||
@@ -368,7 +380,11 @@ class TestAscendDeepseekScalingRotaryEmbedding(TestBase):
|
||||
class TestAscendMRotaryEmbedding(unittest.TestCase):
|
||||
|
||||
def setUp(self):
|
||||
# Common setup for tests
|
||||
self.config_patcher = patch('vllm.config.vllm.get_current_vllm_config')
|
||||
self.mock_get_config = self.config_patcher.start()
|
||||
mock_config = MagicMock()
|
||||
mock_config.compilation_config.custom_ops = ["all"]
|
||||
self.mock_get_config.return_value = mock_config
|
||||
self.number_tokens = 3
|
||||
self.num_head = 8
|
||||
self.num_kvhead = 8
|
||||
|
||||
Reference in New Issue
Block a user