9 lines
274 B
YAML
9 lines
274 B
YAML
model_name: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8"
|
|
accuracy_threshold: 0.29
|
|
num_questions: 1319
|
|
num_fewshot: 5
|
|
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"
|
|
env:
|
|
VLLM_USE_FLASHINFER_MOE_FP8: "1"
|
|
VLLM_FLASHINFER_MOE_BACKEND: "latency"
|