⚠️ New Regressions Detected: 69 failure(s)
gemma3 (NVIDIA multi): • test_model_4b_multiimage • test_model_4b_bf16
gemma3 (NVIDIA single): • test_model_4b_multiimage • test_model_4b_bf16
gemma3n (NVIDIA multi): • test_model_parallelism • test_model_4b_bf16 • test_multi_gpu_data_parallel_forward • test_model_4b_batch • test_model_4b_image • ... and 2 more
gemma3n (NVIDIA single): • test_model_4b_batch • test_model_4b_image • test_model_4b_bf16
llava (NVIDIA multi): • test_small_model_integration_test_llama_batched_regression • test_small_model_integration_test_llama_single • test_generation_siglip_backbone • test_small_model_integration_test • test_small_model_integration_test_batch • ... and 1 more
llava (NVIDIA single): • test_small_model_integration_test_llama_batched_regression • test_small_model_integration_test_llama_single • test_generation_siglip_backbone • test_small_model_integration_test • test_small_model_integration_test_batch • ... and 1 more
whisper (NVIDIA multi): • test_speculative_decoding_non_distil • test_tiny_en_generation • test_whisper_longform_single_batch • test_whisper_longform_multi_batch_hard_prev_cond • test_tiny_en_batched_generation • ... and 17 more
whisper (NVIDIA single): • test_speculative_decoding_non_distil • test_tiny_en_generation • test_whisper_longform_single_batch • test_whisper_longform_multi_batch_hard_prev_cond • test_tiny_en_batched_generation • ... and 16 more