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
|