AssertionError: assert ({'build_comma...ata': {}, ...} == {'build_comma...ata': {}, ...} Omitting 10 identical items, use -vv to show Differing items: {'trt_llm': {'build': {'base_model': 'llama', 'checkpoint_repository': {'repo': 'meta/llama4-500B', 'revision': None, ...ict', 'enable_chunked_context': True, 'kv_cache_free_gpu_mem_fraction': 0.9, 'kv_cache_host_memory_bytes': None, ...}}} != {'trt_llm': {'build': {'base_model': 'llama', 'checkpoint_repository': {'repo': 'meta/llama4-500B', 'source': 'HF'}, 'gather_all_token_logits': False, 'max_batch_size': 512, ...}, 'runtime': {}}} Full diff: { 'build_commands': [], 'environment_variables': {}, 'external_package_dirs': [], 'model_metadata': {}, 'model_name': None, 'python_version': 'py39', 'requirements': [], 'resources': {'accelerator': 'L4', 'cpu': '1', 'memory': '24Gi', 'use_gpu': True}, 'secrets': {}, 'system_packages': [], 'trt_llm': {'build': {'base_model': 'llama', 'checkpoint_repository': {'repo': 'meta/llama4-500B', + 'revision': None, 'source': 'HF'}, 'gather_all_token_logits': False, 'max_batch_size': 512, + 'max_beam_width': 1, + 'max_num_tokens': 8192, + 'max_prompt_embedding_table_size': 0, - 'max_seq_len': 2048}, ? - + 'max_seq_len': 2048, - 'runtime': {}}, + 'num_builder_gpus': None, + 'pipeline_parallel_count': 1, + 'plugin_configuration': {'gemm_plugin': 'auto', + 'paged_kv_cache': True, + 'use_fp8_context_fmha': False, + 'use_paged_context_fmha': True}, + 'quantization_type': 'no_quant', + 'speculator': None, + 'strongly_typed': False, + 'tensor_parallel_count': 1}, + 'runtime': {'batch_scheduler_policy': 'guaranteed_no_evict', + 'enable_chunked_context': True, + 'kv_cache_free_gpu_mem_fraction': 0.9, + 'kv_cache_host_memory_bytes': None, + 'request_default_max_tokens': None, + 'total_token_limit': 500000}}, }) == True