Files
vllm/tests/evals/gsm8k/configs/Qwen3-Next-FP8-EP2.yaml
2026-02-25 17:44:44 -08:00

11 lines
259 B
YAML

model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
accuracy_threshold: 0.85
num_questions: 1319
num_fewshot: 5
server_args: >-
--max-model-len 4096
--tensor-parallel-size 2
--enable-expert-parallel
--async-scheduling
--moe-backend=flashinfer_trtllm