39bdd4cfaa
### What this PR does / why we need it?
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: 李少鹏 <lishaopeng21@huawei.com>
11 lines
203 B
YAML
11 lines
203 B
YAML
model_name: "Qwen/Qwen3-VL-8B-Instruct"
|
|
hardware: "Atlas A2 Series"
|
|
model: "vllm-vlm"
|
|
tasks:
|
|
- name: "mmmu_val"
|
|
metrics:
|
|
- name: "acc,none"
|
|
value: 0.55
|
|
batch_size: 32
|
|
gpu_memory_utilization: 0.7
|