31c29257c8
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
8 lines
259 B
YAML
8 lines
259 B
YAML
model_name: "meta-llama/Llama-4-Scout-17B-16E-Instruct"
|
|
accuracy_threshold: 0.92
|
|
num_questions: 1319
|
|
num_fewshot: 5
|
|
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --enable-expert-parallel"
|
|
env:
|
|
VLLM_USE_FLASHINFER_MOE_FP16: "1"
|