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

[main] rename device type (#5099)

Browse Source 
### What this PR does / why we need it?
Rename `_910B` to `A2`;
Rename `_910_93` to `A3`;
Rename `_910_95` to `A5`;

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: zzzzwwjj <1183291235@qq.com>
This commit is contained in:
zzzzwwjj
2025-12-17 14:08:19 +08:00
committed by GitHub
parent 4144376e88
commit 06b82e7503
16 changed files with 47 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/ut/attention/test_attention_v1.py
View File

@@ -26,7 +26,7 @@ class TestAscendAttentionBackend(TestBase):
AscendAttentionMetadataBuilder)
@patch('vllm_ascend.utils.get_ascend_device_type',
return_value=AscendDeviceType._910_93)
return_value=AscendDeviceType.A3)
def test_get_kv_cache_shape_not_310p(self, mock_soc_version):
result = AscendAttentionBackend.get_kv_cache_shape(10, 20, 30, 40)
self.assertEqual(result, (2, 10, 20, 30, 40))
@@ -103,7 +103,7 @@ class TestAscendAttentionMetadataBuilder(TestBase):
@patch('vllm_ascend.attention.attention_v1.AscendMetadata')
@patch('vllm_ascend.utils.get_ascend_device_type',
return_value=AscendDeviceType._910_93)
return_value=AscendDeviceType.A3)
def test_build_non_310p(self, mock_soc_version, mock_ascend_metadata):
common_attn_metadata = AscendCommonAttentionMetadata(
query_start_loc=torch.tensor([0, 2, 5, 9]),