Files
vllm/tests/evals/gsm8k/configs/Qwen3.5-397B-A17B-NVFP4-DEP2.yaml
2026-03-26 01:21:47 -07:00

10 lines
212 B
YAML

model_name: "nvidia/Qwen3.5-397B-A17B-NVFP4"
accuracy_threshold: 0.88
tolerance: 0.03
num_questions: 1319
num_fewshot: 5
server_args: >-
--max-model-len 4096
--data-parallel-size 2
--enable-expert-parallel