@RunLLM 在vllm的日志里,没有看到图像分辨率相关的配置:
INFO 12-05 19:05:08 [core.py:77] Initializing a V1 LLM engine (v0.11.0) with config: model=‘/msswift_tmp/Qwen3-VL-8B-Instruct’, speculative_config=None, tokenizer=‘/msswift_tmp/Qwen3-VL-8B-Instruct’, skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=10240, download_dir=None, load_format=safetensors, tensor_parallel_size=4, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend=‘auto’, disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser=‘’), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=0, served_model_name=/msswift_tmp/Qwen3-VL-8B-Instruct, enable_prefix_caching=True, chunked_prefill_enabled=True, pooler_config=None, compilation_config={“level”:3,“debug_dump_path”:“”,“cache_dir”:“”,“backend”:“”,“custom_ops”:,“splitting_ops”:[“vllm.unified_attention”,“vllm.unified_attention_with_output”,“vllm.mamba_mixer2”,“vllm.mamba_mixer”,“vllm.short_conv”,“vllm.linear_attention”,“vllm.plamo2_mamba_mixer”,“vllm.gdn_attention”,“vllm.sparse_attn_indexer”],“use_inductor”:true,“compile_sizes”:,“inductor_compile_config”:{“enable_auto_functionalized_v2”:false},“inductor_passes”:{},“cudagraph_mode”:[2,1],“use_cudagraph”:true,“cudagraph_num_of_warmups”:1,“cudagraph_capture_sizes”:[512,504,496,488,480,472,464,456,448,440,432,424,416,408,400,392,384,376,368,360,352,344,336,328,320,312,304,296,288,280,272,264,256,248,240,232,224,216,208,200,192,184,176,168,160,152,144,136,128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],“cudagraph_copy_inputs”:false,“full_cuda_graph”:false,“use_inductor_graph_partition”:false,“pass_config”:{},“max_capture_size”:512,“local_cache_dir”:null}