[Test]Add accuracy test for multiple models (#3823)

### What this PR does / why we need it?
Add accuracy test for multiple models:
- Meta_Llama_3.1_8B_Instruct
- Qwen2.5-Omni-7B
- Qwen3-VL-8B-Instruct

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
ZengSilong
2025-11-04 14:46:39 +08:00
committed by GitHub
parent e9bb4491ec
commit dc1a6cb503
9 changed files with 46 additions and 8 deletions

View File

@@ -1,5 +1,4 @@
model_name: "Qwen/Qwen3-30B-A3B"
runner: "linux-aarch64-a2-2"
hardware: "Atlas A2 Series"
tasks:
- name: "gsm8k"
@@ -17,4 +16,4 @@ gpu_memory_utilization: 0.6
enable_expert_parallel: True
tensor_parallel_size: 2
apply_chat_template: False
fewshot_as_multiturn: False
fewshot_as_multiturn: False