8 lines
232 B
YAML
8 lines
232 B
YAML
|
model_name: "nvidia/Llama-4-Scout-17B-16E-Instruct-FP8"
|
||
|
|
accuracy_threshold: 0.92
|
||
|
|
num_questions: 1319
|
||
|
|
num_fewshot: 5
|
||
|
|
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"
|
||
|
|
env:
|
||
|
|
VLLM_TEST_FORCE_FP8_MARLIN: "1"
|