6cb76ecd02
### What this PR does / why we need it?
[Nightly] Avoid max_model_len being smaller than the decoder prompt to
prevent single-node-accuray-tests from failing
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: ZT-AIA <1028681969@qq.com>
Signed-off-by: ZT-AIA <63220130+ZT-AIA@users.noreply.github.com>
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
|