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

Remove VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE (#5272)

Browse Source 
`VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE` is only used together with
`VLLM_ASCEND_ENABLE_PREFETCH_MLP` which is useless totally. This PR
remove it.
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-12-25 11:09:56 +08:00
committed by GitHub
parent 13cd6362c6
commit 2ae0bad96d
8 changed files with 7 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/e2e/multicard/test_offline_inference_distributed.py
View File

@@ -178,7 +178,6 @@ def test_deepseek_v2_lite_fc1_tp2() -> None:
@pytest.mark.parametrize("model", QWEN_DENSE_MODELS)
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE": "1"})
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_FLASHCOMM1": "1"})
def test_qwen3_dense_fc1_tp2(model):
example_prompts = [
@@ -197,7 +196,6 @@ def test_qwen3_dense_fc1_tp2(model):
@pytest.mark.parametrize("model", QWEN_DENSE_MODELS)
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE": "1"})
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_PREFETCH_MLP": "1"})
def test_qwen3_dense_prefetch_mlp_weight_tp2(model):
example_prompts = [