diff --git a/tests/e2e/models/configs/Qwen3-VL-30B-A3B-Instruct.yaml b/tests/e2e/models/configs/Qwen3-VL-30B-A3B-Instruct.yaml index 9c98249c..5b5dc050 100644 --- a/tests/e2e/models/configs/Qwen3-VL-30B-A3B-Instruct.yaml +++ b/tests/e2e/models/configs/Qwen3-VL-30B-A3B-Instruct.yaml @@ -6,6 +6,7 @@ tasks: metrics: - name: "acc,none" value: 0.58 +max_model_len: 8192 tensor_parallel_size: 2 gpu_memory_utilization: 0.7 enable_expert_parallel: True diff --git a/tests/e2e/models/configs/Qwen3-VL-8B-Instruct.yaml b/tests/e2e/models/configs/Qwen3-VL-8B-Instruct.yaml index 96581e54..8803a120 100644 --- a/tests/e2e/models/configs/Qwen3-VL-8B-Instruct.yaml +++ b/tests/e2e/models/configs/Qwen3-VL-8B-Instruct.yaml @@ -6,5 +6,6 @@ tasks: metrics: - name: "acc,none" value: 0.55 +max_model_len: 8192 batch_size: 32 gpu_memory_utilization: 0.7