[Bugfix] Fix deepseek percision issue and add acc ci for it (#905)

### What this PR does / why we need it?
Fix deepseek percision issue on V0 and add acc ci for it
Fixes https://github.com/vllm-project/vllm-ascend/issues/1062
### How was this patch tested?
CI passed with new added test.

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-06-04 20:26:44 +08:00
committed by GitHub
parent da9acfca60
commit afc4c0cd03
9 changed files with 121 additions and 43 deletions

View File

@@ -22,7 +22,6 @@ Run `pytest tests/test_offline_inference.py`.
"""
import os
import pytest
import vllm # noqa: F401
from tests.conftest import VllmRunner
@@ -47,7 +46,6 @@ def test_models_distributed_QwQ():
vllm_model.generate_greedy(example_prompts, max_tokens)
@pytest.mark.skipif(True, reason="wait for mla issue fixed on v1")
def test_models_distributed_DeepSeek():
example_prompts = [
"vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.",