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

remove useless patch (#4699)

Browse Source 
patach_config is useless now. Let's remove it


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

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
This commit is contained in:
wangxiyuan
2025-12-08 11:02:42 +08:00
committed by GitHub
parent 866347a621
commit 0b65ac6c4b
21 changed files with 30 additions and 277 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/ut/torchair/test_torchair_model_runner.py
View File

@@ -21,7 +21,7 @@ class TestNPUTorchairModelRunner(PytestBase):
runner.vllm_config = MagicMock(spec=VllmConfig)
runner.speculative_config = MagicMock(
method="deepseek_mtp",
method="mtp",
num_speculative_tokens=4,
disable_padded_drafter_batch=False)

2
tests/ut/torchair/test_torchair_mtp_proposer.py
View File

@@ -19,7 +19,7 @@ class TestTorchairMtpProposer(PytestBase):
vllm_config.speculative_config = MagicMock()
vllm_config.speculative_config.draft_model_config = MagicMock()
vllm_config.speculative_config.draft_model_config.dtype = torch.float16
vllm_config.speculative_config.method = "deepseek_mtp"
vllm_config.speculative_config.method = "mtp"
vllm_config.speculative_config.num_speculative_tokens = 5
vllm_config.load_config = MagicMock()
cache_config = CacheConfig(block_size=16)