Files
vllm/tests/evals/gsm8k/configs/moe-refactor-dp-ep/Qwen3-30B-A3B-BF16-triton.yaml
2026-01-15 12:53:40 -08:00

6 lines
193 B
YAML

model_name: "Qwen/Qwen3-30B-A3B"
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"