efa0f64f22
### What this PR does / why we need it?
Add tutorials for `Qwen3-VL-30B-A3B-Instruct`.
- vLLM version: release/v0.13.0
- vLLM main:
bc0a5a0c08
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
13 lines
268 B
YAML
13 lines
268 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: 128000
|
|
tensor_parallel_size: 2
|
|
gpu_memory_utilization: 0.7
|
|
enable_expert_parallel: True
|