Files
vllm/tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-Fp8-CT-vllm-cutlass.yaml

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

6 lines
203 B
YAML
Raw Normal View History

model_name: "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic"
accuracy_threshold: 0.92
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"