CookieApril/enginex-ascend-910-vllm
1
0
Fork 0
forked from EngineX-Ascend/enginex-ascend-910-vllm
Code Pull Requests Activity

init v0.11.0rc0

Browse Source
This commit is contained in:
luopingyi
2025-10-14 10:38:28 +08:00
parent 67afd0ea78
commit 66dc16f966
278 changed files with 28130 additions and 11708 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
tests/e2e/multicard/test_expert_parallel.py
View File

@@ -14,14 +14,24 @@ def test_e2e_ep_correctness(model_name):
]
max_tokens = 5
with VllmRunner(model_name, tensor_parallel_size=2,
enforce_eager=True) as vllm_model:
# FIXME: Really strange that chunked prefill might lead to different results, investigate further
with VllmRunner(
model_name,
tensor_parallel_size=2,
additional_config={"ascend_scheduler_config": {
"enabled": True
}},
enforce_eager=True) as vllm_model:
tp_output = vllm_model.generate_greedy(example_prompts, max_tokens)
with VllmRunner(model_name,
tensor_parallel_size=2,
enable_expert_parallel=True,
enforce_eager=True) as vllm_model:
with VllmRunner(
model_name,
tensor_parallel_size=2,
enable_expert_parallel=True,
additional_config={"ascend_scheduler_config": {
"enabled": True
}},
enforce_eager=True) as vllm_model:
ep_output = vllm_model.generate_greedy(example_prompts, max_tokens)
check_outputs_equal(