== gpu ==
index, name, memory.total [MiB], driver_version
0, NVIDIA RTX PRO 6000 Blackwell Server Edition, 97887 MiB, 595.91.07
== cpu/mem ==
1
               total        used        free      shared  buff/cache   available
Mem:            2267         275         181           1        1810        1970
== mount ==
mfs#euro-3.runpod.net:9421 on /data type fuse (rw,nosuid,nodev,relatime,user_id=0,group_id=0,allow_other)
== disk ==
/data 183.4 GB
blend 60.8 GB
== python ==
Python 3.11.10
== engine ==
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m INFO 09-02 18:11:47 [core.py:77] Initializing a V1 LLM engine (v0.11.0) with config: model='/data/blend', speculative_config=None, tokenizer='/data/blend', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=8192, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=mxfp4, 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='openai_gptoss'), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=1234, served_model_name=/data/blend, 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":[992,976,960,944,928,912,896,880,864,848,832,816,800,784,768,752,736,720,704,688,672,656,640,624,608,592,576,560,544,528,512,496,480,464,448,432,416,400,384,368,352,336,320,304,288,272,256,248,240,232,224,216,208,200,192,184,176,168,160,152,144,136,128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],"cudagraph_copy_inputs":false,"full_cuda_graph":false,"use_inductor_graph_partition":false,"pass_config":{},"max_capture_size":992,"local_cache_dir":null}
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m WARNING 09-02 18:11:48 [topk_topp_sampler.py:66] FlashInfer is not available. Falling back to the PyTorch-native implementation of top-p & top-k sampling. For the best performance, please install FlashInfer.
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m INFO 09-02 18:11:48 [cuda.py:361] Using Triton backend on V1 engine.
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m INFO 09-02 18:11:48 [mxfp4.py:98] Using Marlin backend
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m WARNING 09-02 18:13:51 [marlin_utils_fp4.py:196] Your GPU does not have native support for FP4 computation but FP4 quantization is being used. Weight-only FP4 compression will be used leveraging the Marlin kernel. This may degrade performance for compute-heavy workloads.
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m INFO 09-02 18:13:52 [gpu_model_runner.py:2653] Model loading took 65.9651 GiB and 123.527245 seconds
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m INFO 09-02 18:14:26 [gpu_worker.py:298] Available KV cache memory: 12.03 GiB
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m INFO 09-02 18:14:26 [kv_cache_utils.py:1087] GPU KV cache size: 175,264 tokens
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m INFO 09-02 18:14:26 [kv_cache_utils.py:1091] Maximum concurrency for 8,192 tokens per request: 21.37x
[1;36m(EngineCore_DP0 pid=1971)[0;0m [1;36m(EngineCore_DP0 pid=1971)[0;0m INFO 09-02 18:14:38 [core.py:210] init engine (profile, create kv cache, warmup model) took 45.37 seconds
