tests/evals/gsm8k/configs/moe-refactor/Llama-4-Scout-BF16-fi-cutlass.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"
[MoE Refactor][17/N] Apply Refactor to Bf16 (#31827) Signed-off-by: Yongye Zhu <zyy1102000@gmail.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> 2026-01-15 12:53:40 -08:00			`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"`