tests/evals/gsm8k/configs/Qwen3-30B-A3B-NVFP4.yaml

model_name: "nvidia/Qwen3-30B-A3B-FP4"
accuracy_threshold: 0.89
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 4096"
[CI] Add Qwen3 MoE NVFP4 to Blackwell lm-eval (#26316) Signed-off-by: mgoin <mgoin64@gmail.com> 2025-10-07 13:36:15 -04:00			`model_name: "nvidia/Qwen3-30B-A3B-FP4"`
			`accuracy_threshold: 0.89`
			`num_questions: 1319`
			`num_fewshot: 5`
[CI] Generalize gsm8k test args and add Qwen3-Next MTP B200 test (#30723) Signed-off-by: mgoin <mgoin64@gmail.com> 2025-12-16 14:28:34 -05:00			`server_args: "--enforce-eager --max-model-len 4096"`