{"version":"0.29.0"}
vllm:cache_config_info{_block_size_resolved="True",block_size="16",cache_dtype="auto",enable_prefix_caching="False",engine="0",gpu_memory_utilization="0.92",is_attention_free="False",kv_cache_dtype_skip_layers="[]",kv_cache_layout="None",kv_cache_max_concurrency="292.5625",kv_cache_memory_bytes="17179869184",kv_cache_size_tokens="299584",kv_offloading_backend="native",kv_offloading_size="None",kv_sharing_fast_prefill="False",mamba_block_size="None",mamba_cache_dtype="auto",mamba_cache_mode="none",mamba_page_size_padded="None",mamba_ssm_cache_dtype="auto",num_cpu_blocks="None",num_gpu_blocks="18724",num_gpu_blocks_override="None",prefix_cache_retention_interval="0",prefix_caching_hash_algo="sha256",prefix_match_unit="None",replayssm_buffer_len="16",skip_page_size_padded="None",sliding_window="None",use_kda_recoverssm="False",use_replayssm="False",user_specified_block_size="False",user_specified_mamba_block_size="False"} 1.0
{'max_num_seqs': 256, 'max_num_batched_tokens': 2048, 'enable_chunked_prefill': True}
vllm:num_requests_running{engine="0",model_name="Qwen/Qwen2.5-7B-Instruct"} 0.0
vllm:num_requests_waiting{engine="0",model_name="Qwen/Qwen2.5-7B-Instruct"} 0.0
content events: 257
reasoning events: 0