Files
vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-fi-cutlass.yaml
2026-02-25 17:44:44 -08:00

6 lines
222 B
YAML

model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
accuracy_threshold: 0.88
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_cutlass"