305820f1a9
### What this PR does / why we need it?
Adapt to the model type of Qwen3-VL-8B-Instruct-W8A8
- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
12 lines
255 B
YAML
12 lines
255 B
YAML
model_name: "vllm-ascend/Qwen3-VL-8B-Instruct-W8A8"
|
|
hardware: "Atlas A2 Series"
|
|
model: "vllm-vlm"
|
|
tasks:
|
|
- name: "mmmu_val"
|
|
metrics:
|
|
- name: "acc,none"
|
|
value: 0.52
|
|
max_model_len: 8192
|
|
batch_size: 32
|
|
gpu_memory_utilization: 0.8
|
|
quantization: ascend |