tests/evals/gsm8k/configs/Qwen3.5-397B-A17B-NVFP4-DEP2.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
  --max-num-seqs 512
[Bugfix] Fix DeepGemm E8M0 accuracy degradation for Qwen3.5 FP8 on Blackwell (#38083) Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com> 2026-03-26 12:21:47 +04:00			`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`
[CI] fix LM Eval Qwen3.5 Models (B200) (#38632) Signed-off-by: zjy0516 <riverclouds.zhu@qq.com> 2026-03-31 21:20:08 +08:00			`--max-num-seqs 512`