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

6
tests/ut/ops/test_fused_moe.py
View File

@@ -127,7 +127,7 @@ def mock_dist_env(mocker: MockerFixture):
return_value=mock_forward_context_obj), \
patch('vllm_ascend.ops.fused_moe.prepare_finalize.get_forward_context',
return_value=mock_forward_context_obj), \
patch("vllm_ascend.utils.get_ascend_device_type", return_value=AscendDeviceType._910_93), \
patch("vllm_ascend.utils.get_ascend_device_type", return_value=AscendDeviceType.A3), \
patch('vllm_ascend.ops.fused_moe.moe_mlp.get_forward_context',
return_value=mock_forward_context_obj), \
patch('vllm_ascend.ops.fused_moe.moe_comm_method.MC2CommImpl._get_token_dispatcher',
@@ -323,7 +323,7 @@ class TestUnifiedApplyMLP(TestBase):
@patch('vllm_ascend.ops.fused_moe.moe_mlp.get_forward_context')
@patch('vllm_ascend.utils.get_ascend_device_type',
return_value=AscendDeviceType._910_93)
return_value=AscendDeviceType.A3)
@patch('torch_npu.npu_grouped_matmul')
@patch('torch_npu.npu_dynamic_quant')
@patch('torch_npu.npu_dequant_swiglu_quant')
@@ -386,7 +386,7 @@ class TestUnifiedApplyMLP(TestBase):
self.assertEqual(result.dtype, torch.bfloat16)
@patch('vllm_ascend.utils.get_ascend_device_type',
return_value=AscendDeviceType._910_93)
return_value=AscendDeviceType.A3)
@patch('torch_npu.npu_grouped_matmul')
@patch('torch_npu.npu_swiglu')
@patch('torch_npu.npu_dynamic_quant')