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

[Misc][V0 Deprecation] Remove V0 related codes of test, example, platform (#1805)

Browse Source 
### What this PR does / why we need it?
Remove V0 related codes of test, example, platform.

This PR is a part of
https://github.com/vllm-project/vllm-ascend/issues/1620.

- vLLM version: v0.9.2
- vLLM main:
235bfd5dfe

---------

Signed-off-by: shen-shanshan <467638484@qq.com>
This commit is contained in:
Shanshan Shen
2025-07-15 19:58:55 +08:00
committed by GitHub
parent a929699e98
commit f96100fad5
5 changed files with 10 additions and 460 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
tests/ut/test_platform.py
View File

@@ -481,45 +481,6 @@ class TestNPUPlatform(TestBase):
result,
"vllm_ascend.attention.attention_v1.AscendAttentionBackend")
@patch('vllm_ascend.platform.get_ascend_config')
def test_get_attn_backend_cls_use_mla_only(self, mock_get_ascend_config):
mock_config = MagicMock()
mock_config.torchair_graph_config.enabled = False
mock_get_ascend_config.return_value = mock_config
result = self.platform.get_attn_backend_cls(
selected_backend="ascend",
head_size=64,
dtype="float16",
kv_cache_dtype="float16",
block_size=64,
use_v1=False,
use_mla=True,
)
self.assertEqual(
result,
"vllm_ascend.attention.attention.AscendMLAAttentionBackend")
@patch('vllm_ascend.platform.get_ascend_config')
def test_get_attn_backend_cls_default_case(self, mock_get_ascend_config):
mock_config = MagicMock()
mock_config.torchair_graph_config.enabled = False
mock_get_ascend_config.return_value = mock_config
result = self.platform.get_attn_backend_cls(
selected_backend="ascend",
head_size=64,
dtype="float16",
kv_cache_dtype="float16",
block_size=64,
use_v1=False,
use_mla=False,
)
self.assertEqual(
result, "vllm_ascend.attention.attention.AscendAttentionBackend")
def test_get_punica_wrapper(self):
result = self.platform.get_punica_wrapper()
self.assertEqual(