|
1
|
model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block" |
|
2
|
accuracy_threshold: 0.85 |
|
3
|
num_questions: 1319 |
|
4
|
num_fewshot: 5 |
|
5
|
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2" |
|
6
|
env: |
|
7
|
VLLM_USE_DEEP_GEMM: "1" |
|
8
|
VLLM_USE_DEEP_GEMM_MOE: "1" |