13 lines
266 B
YAML
13 lines
266 B
YAML
|
model_name: "Qwen/Qwen3-VL-30B-A3B-Instruct"
|
||
|
|
hardware: "Atlas A2 Series"
|
||
|
|
model: "vllm-vlm"
|
||
|
|
tasks:
|
||
|
|
- name: "mmmu_val"
|
||
|
|
metrics:
|
||
|
|
- name: "acc,none"
|
||
|
|
value: 0.58
|
||
|
|
max_model_len: 8192
|
||
|
|
tensor_parallel_size: 2
|
||
|
|
gpu_memory_utilization: 0.7
|
||
|
|
enable_expert_parallel: True
|