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

[Misc] Refactor additional_config (#1029)

Browse Source 
More and more config options are added to additional_config. This PR
provide a new AscendConfig to manage these config options by an easier
way to make code cleaner and readable.

 This PR also added the `additional_config` doc for users.

Added the test_ascend_config.py to make sure the new AscendConfig works
as expect.

TODO: Add e2e test with torchair and deepseek once the CI resource is
available.

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-06-05 16:28:01 +08:00
committed by GitHub
parent 7737aaa40f
commit e1ab6d318e
23 changed files with 456 additions and 208 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/multicard/test_dynamic_npugraph_batchsize.py
View File

@@ -18,8 +18,6 @@ import pytest
import torch
from vllm import LLM, SamplingParams
from vllm_ascend.utils import vllm_version_is
MODELS = [
"Qwen/Qwen2.5-0.5B-Instruct",
]
@@ -32,9 +30,6 @@ prompts = [
]
@pytest.mark.skipif(
(vllm_version_is("0.8.5") or vllm_version_is("0.8.5.post1")),
reason="aclgraph not supported in v0.8.5 and v0.8.5.post1")
@pytest.mark.parametrize("model", MODELS)
@pytest.mark.parametrize("tp_size", TENSOR_PARALLELS)
@pytest.mark.parametrize("max_tokens", [64])

8
tests/multicard/test_offline_inference_distributed.py
View File

@@ -31,9 +31,7 @@ os.environ["PYTORCH_NPU_ALLOC_CONF"] = "max_split_size_mb:256"
def test_models_distributed_QwQ():
example_prompts = [
"vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.",
"Briefly describe the major milestones in the development of artificial intelligence from 1950 to 2020.",
"Compare and contrast artificial intelligence with human intelligence in terms of processing information.",
"Hello, my name is",
]
dtype = "half"
max_tokens = 5
@@ -48,9 +46,7 @@ def test_models_distributed_QwQ():
def test_models_distributed_DeepSeek():
example_prompts = [
"vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.",
"Briefly describe the major milestones in the development of artificial intelligence from 1950 to 2020.",
"Compare and contrast artificial intelligence with human intelligence in terms of processing information.",
"Hello, my name is",
]
dtype = "half"
max_tokens = 5