upgrade to vllm 0.11.2 (#4400)
Bump vLLM version to v0.11.2 What's broken and changed by vLLM: 1. structured_output is broken by https://github.com/vllm-project/vllm/pull/26866 2. get_mrope_input_positions is broken by https://github.com/vllm-project/vllm/pull/28399 3. graph mode is broken by https://github.com/vllm-project/vllm/pull/25110 we'll upgrade torch to 2.8 to fix the problem later 4. embedding is broken by https://github.com/vllm-project/vllm/pull/27583 5. `get_attn_backend_cls` and attention backend is broken are broken by https://github.com/vllm-project/vllm/pull/28534 6. spec decode is broken by https://github.com/vllm-project/vllm/pull/28771 7. sp feature is broken by https://github.com/vllm-project/vllm/pull/27126 8. mtp is broken by https://github.com/vllm-project/vllm/pull/27922 9. lora is broken by https://github.com/vllm-project/vllm/pull/21068 10. execute_model is broken by https://github.com/vllm-project/vllm/pull/26866 11. `VLLM_DISABLE_SHARED_EXPERTS_STREAM` env is broken by https://github.com/vllm-project/vllm/pull/28159 12. kv cahe is broken by https://github.com/vllm-project/vllm/pull/27753 13. dp is broken by https://github.com/vllm-project/vllm/pull/25110 What's broken and changed by ourself: 1. qwen vl is broken by https://github.com/vllm-project/vllm/pull/28455 We'll remove model files in the future to avoid this kind of error 2. Engine core is broken by https://github.com/vllm-project/vllm/pull/23691 We'll remove the patch file in the future. 3. Ascend scheduler is broken by https://github.com/vllm-project/vllm/pull/28733 We'll remove ascend scheudler later. 4. qwen3-next is broken by https://github.com/vllm-project/vllm/pull/28083 We'll remove model files in the future to avoid this kind of error 5. qwen vl is broken by https://github.com/vllm-project/vllm/pull/27764. We'll remove model files in the future Known issue: 1. ray doesn't work 2. the accuracy of qwen3-next is not correct 3. qwen3-vl is broken 4. prefix cache+ ascend scheduler + deepseek v2 lite is broken. Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com> Co-authored-by: 22dimensions <waitingwind@foxmail.com> Co-authored-by: shen-shanshan <467638484@qq.com> - vLLM version: v0.11.2 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com> Signed-off-by: leo-pony <nengjunma@outlook.com> Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com>
This commit is contained in:
wangxiyuan
@@ -107,8 +107,7 @@ class TestACLGraphWrapper(TestBase):
|
||||
|
||||
wrapper = ACLGraphWrapper(runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool)
|
||||
runtime_mode=CUDAGraphMode.FULL)
|
||||
|
||||
self.assertEqual(wrapper.runnable, self.mock_runnable)
|
||||
self.assertEqual(wrapper.vllm_config, self.mock_vllm_config)
|
||||
@@ -130,7 +129,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
self.assertEqual(wrapper.runnable, self.mock_runnable)
|
||||
@@ -152,8 +150,7 @@ class TestACLGraphWrapper(TestBase):
|
||||
with self.assertRaises(AssertionError):
|
||||
ACLGraphWrapper(runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.NONE,
|
||||
graph_pool=self.mock_graph_pool)
|
||||
runtime_mode=CUDAGraphMode.NONE)
|
||||
|
||||
@patch('vllm_ascend.compilation.acl_graph.get_forward_context')
|
||||
@patch('vllm_ascend.compilation.acl_graph.current_platform')
|
||||
@@ -171,7 +168,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
result = wrapper("arg1", "arg2")
|
||||
@@ -196,7 +192,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
result = wrapper("arg1", "arg2")
|
||||
@@ -247,7 +242,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
# Create a real torch tensor for the test, not a mock
|
||||
@@ -319,7 +313,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
# Create a real torch tensor for the test, not a mock
|
||||
@@ -392,7 +385,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
# First call to capture the graph
|
||||
@@ -447,7 +439,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
# First call to capture the graph
|
||||
@@ -518,7 +509,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
# Create a real torch tensor for the test, not a mock
|
||||
@@ -588,7 +578,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
# Create a real torch tensor for the test, not a mock
|
||||
@@ -659,7 +648,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
# Create a real torch tensor for the test, not a mock
|
||||
@@ -680,7 +668,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
# Should be able to access attributes of the runnable
|
||||
@@ -699,7 +686,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
# Should raise AttributeError for non-existent attributes
|
||||
@@ -715,7 +701,6 @@ class TestACLGraphWrapper(TestBase):
|
||||
runnable=self.mock_runnable,
|
||||
vllm_config=self.mock_vllm_config,
|
||||
runtime_mode=CUDAGraphMode.FULL,
|
||||
graph_pool=self.mock_graph_pool,
|
||||
cudagraph_options=self.mock_cudagraph_options)
|
||||
|
||||
unwrapped = wrapper.unwrap()
|
||||
|
||||
Reference in New Issue
Block a user