Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
6 lines
236 B
YAML
6 lines
236 B
YAML
model_name: "RedHatAI/Qwen3-30B-A3B-NVFP4"
|
|
accuracy_threshold: 0.88
|
|
num_questions: 1319
|
|
num_fewshot: 5
|
|
server_args: "--enforce-eager --max-model-len 8192 --data-parallel-size 2 --enable-expert-parallel --moe-backend=flashinfer_cutlass"
|