tests/evals/gsm8k/configs/Qwen3-0.6B-FP8.yaml

model_name: "Qwen/Qwen3-0.6B-FP8"
accuracy_threshold: 0.375
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 4096"
[CI/Build] Replace lm-eval gsm8k tests with faster implementation (#23002) Signed-off-by: mgoin <mgoin64@gmail.com> 2025-08-19 18:07:30 -04:00			`model_name: "Qwen/Qwen3-0.6B-FP8"`
			`accuracy_threshold: 0.375`
			`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"`