[2026-10-17 14:30:54] Registered linear attn model: config=GigaChat35Config, backend=GDNAttnBackend, archs=['GigaChat35ForCausalLM', 'GigaChat35ForCausalLMNextN']
[2026-10-17 14:30:56] Failed to get GPU memory capacity from nvidia-smi. Falling back to torch.cuda.mem_get_info(). Reported total GPU memory per device (MiB): [124610], using min: 124610 MiB.
[2026-10-17 14:30:56] Attention backend not specified. Use flashinfer backend by default.
[2026-10-17 14:30:57] server_args={'model_path': 'Qwen/Qwen3-30B-A3B-Instruct-2507', 'tokenizer_path': 'Qwen/Qwen3-30B-A3B-Instruct-2507', 'tokenizer_mode': 'auto', 'tokenizer_backend': 'huggingface', 'tokenizer_worker_num': 1, 'detokenizer_worker_num': 1, 'skip_tokenizer_init': False, 'load_format': 'auto', 'model_loader_extra_config': '{}', 'trust_remote_code': False, 'context_length': None, 'is_embedding': False, 'enable_multimodal': None, 'revision': None, 'model_impl': 'auto', 'model_config_parser': 'auto', 'json_model_override_args': '{}', 'dtype': 'auto', 'quantization': None, 'quantization_param_path': None, 'kv_cache_dtype': 'auto', 'enable_fp32_lm_head': False, 'modelopt_quant': None, 'modelopt_checkpoint_restore_path': None, 'modelopt_checkpoint_save_path': None, 'modelopt_export_path': None, 'quantize_and_serve': False, 'rl_quant_profile': None, 'enable_tf32_matmul': False, 'mem_fraction_static': 0.7, 'max_running_requests': None, 'max_queued_requests': None, 'max_total_tokens': None, 'chunked_prefill_size': 8192, 'prefill_decode_interval': 0, 'enable_dynamic_chunking': False, 'max_prefill_tokens': 16384, 'prefill_max_requests': None, 'schedule_policy': 'fcfs', 'enable_priority_scheduling': False, 'disable_priority_preemption': False, 'default_priority_value': None, 'abort_on_priority_when_disabled': False, 'schedule_low_priority_values_first': False, 'priority_scheduling_preemption_threshold': 10, 'retraction_policy': 'length', 'schedule_conservativeness': 1.0, 'page_size': 1, 'c128_page_size': 16, 'swa_full_tokens_ratio': 0.8, 'disable_hybrid_swa_memory': False, 'radix_eviction_policy': 'lru', 'radix_eviction_policy_config': None, 'prefill_only_disable_kv_cache': False, 'disable_radix_cache': False, 'enable_page_major_kv_layout': False, 'enable_unified_memory': False, 'disable_chunked_prefix_cache': False, 'disable_overlap_schedule': False, 'num_continuous_decode_steps': 1, 'scheduler_recv_interval': 1, 'enable_mixed_chunk': False, 'nccl_port': None, 'dist_timeout': None, 'dist_init_addr': None, 'gated_launch_port': None, 'nnodes': 1, 'node_rank': 0, 'tp_size': 1, 'dcp_size': 1, 'pp_size': 1, 'pp_max_micro_batch_size': None, 'pp_async_batch_depth': 0, 'dp_size': 1, 'attn_dp_size': 1, 'load_balance_method': 'round_robin', 'attn_cp_size': 1, 'moe_dp_size': 1, 'dwdp_size': 1, 'dcp_comm_backend': 'ag_rs', 'dcp_replicate_q_proj': None, 'enable_prefill_cp': False, 'cp_strategy': None, 'enable_dsa_cache_layer_split': False, 'enable_cp_decode_attn_tp': False, 'enable_kv_cache_sharding': False, 'enable_dp_attention': False, 'enable_dp_attention_local_control_broadcast': False, 'enable_dp_lm_head': False, 'enable_tp_lm_head_all_to_all': False, 'enable_attn_tp_input_scattered': False, 'enable_shared_experts_attn_tp': False, 'shared_experts_tp_size': None, 'enable_dense_mlp_attn_tp': False, 'enable_layernorm_sp': False, 'disable_attn_tp_gather': False, 'enable_p2p_check': False, 'device': 'cuda', 'base_gpu_id': 0, 'gpu_id_step': 1, 'random_seed': 767446753, 'mlx_enable_sampling': False, 'watchdog_timeout': 300, 'soft_watchdog_timeout': None, 'sleep_on_idle': False, 'use_ray': False, 'custom_sigquit_handler': None, 'numa_node': None, 'gc_threshold': None, 'host': '127.0.0.1', 'port': 30000, 'fastapi_root_path': '', 'smg_grpc_mode': False, 'grpc_mode': False, 'grpc_port': None, 'grpc_worker_threads': 4, 'sidecar': None, 'sidecar_args': None, 'skip_server_warmup': False, 'warmups': None, 'enable_http2': False, 'http2_max_concurrent_streams': 200, 'http2_initial_connection_window_size': 1048576, 'ssl_keyfile': None, 'ssl_certfile': None, 'ssl_ca_certs': None, 'ssl_keyfile_password': None, 'enable_ssl_refresh': False, 'api_key': None, 'admin_api_key': None, 'served_model_name': 'Qwen/Qwen3-30B-A3B-Instruct-2507', 'weight_version': 'default', 'chat_template': None, 'trust_request_chat_template': False, 'hf_chat_template_name': None, 'completion_template': None, 'file_storage_path': None, 'enable_cache_report': True, 'return_input_ids': False, 'return_output_ids': False, 'reasoning_parser': None, 'default_chat_template_kwargs': None, 'strip_thinking_cache': False, 'enable_strict_thinking': False, 'tool_call_parser': None, 'tool_server': None, 'sampling_defaults': 'model', 'asr_max_buffer_seconds': 60, 'asr_max_concurrent_sessions': 32, 'preferred_sampling_params': None, 'allow_auto_truncate': False, 'stream_interval': 1, 'batch_notify_size': 16, 'stream_response_default_include_usage': False, 'incremental_streaming_output': False, 'enable_streaming_session': False, 'enable_session_radix_cache': False, 'log_level': 'info', 'log_level_http': None, 'log_requests': False, 'log_requests_level': 2, 'log_requests_format': 'text', 'log_requests_target': None, 'uvicorn_access_log_exclude_prefixes': [], 'crash_dump_folder': None, 'show_time_cost': False, 'enable_metrics': True, 'smg_http_sidecar_port': None, 'enable_mfu_metrics': False, 'enable_metrics_for_all_schedulers': False, 'load_snapshot_publish_interval': 15, 'tokenizer_metrics_custom_labels_header': 'x-custom-labels', 'tokenizer_metrics_allowed_custom_labels': None, 'extra_metric_labels': None, 'bucket_time_to_first_token': None, 'bucket_inter_token_latency': None, 'bucket_e2e_request_latency': None, 'prompt_tokens_buckets': None, 'generation_tokens_buckets': None, 'gc_warning_threshold_secs': 0.0, 'decode_log_interval': 40, 'enable_request_time_stats_logging': False, 'kv_events_config': None, 'load_publish_endpoint': None, 'enable_forward_pass_metrics': False, 'forward_pass_metrics_worker_id': '', 'forward_pass_metrics_ipc_name': None, 'enable_trace': False, 'trace_modules': 'request', 'otlp_traces_endpoint': 'localhost:4317', 'export_metrics_to_file': False, 'export_metrics_to_file_dir': None, 'stat_loggers': None, 'constrained_json_whitespace_pattern': None, 'constrained_json_disable_any_whitespace': False, 'constrained_json_max_whitespace_cnt': None, 'attention_backend': 'flashinfer', 'decode_attention_backend': None, 'enable_lean_attention': None, 'prefill_attention_backend': None, 'sampling_backend': 'flashinfer', 'grammar_backend': 'xgrammar', 'radix_cache_backend': None, 'mm_attention_backend': None, 'fp8_gemm_runner_backend': 'auto', 'fp4_gemm_runner_backend': 'auto', 'bf16_gemm_backend': 'auto', 'dsa_prefill_backend': None, 'dsv4_prefill_backend': 'auto', 'dsa_decode_backend': None, 'dsa_paged_mqa_logits_backend': 'auto', 'dsa_topk_backend': 'sgl-kernel', 'disable_flashinfer_autotune': False, 'flashinfer_autotune_skip_ops': None, 'mamba_backend': 'triton', 'cuda_graph_config': {'decode': {'backend': 'disabled', 'max_bs': 256, 'bs': [1, 2, 4, 8, 12, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256], 'tc_compiler': 'eager', 'max_context_size': None, 'full_prefill_max_req': None, 'full_prefill_prefix_chunk_tokens': None, 'max_seq_len': None}, 'prefill': {'backend': 'disabled', 'max_bs': 8192, 'bs': [4, 8, 12, 16, 20, 24, 28, 32, 48, 64, 80, 96, 112, 128, 144, 160, 176, 192, 208, 224, 240, 256, 288, 320, 352, 384, 416, 448, 480, 512, 576, 640, 704, 768, 832, 896, 960, 1024, 1280, 1536, 1792, 2048, 2304, 2560, 2816, 3072, 3328, 3584, 3840, 4096, 4608, 5120, 5632, 6144, 6656, 7168, 7680, 8192], 'tc_compiler': 'eager', 'max_context_size': None, 'full_prefill_max_req': None, 'full_prefill_prefix_chunk_tokens': None, 'max_seq_len': None}}, 'cuda_graph_backend_decode': 'disabled', 'cuda_graph_backend_prefill': 'disabled', 'cuda_graph_max_bs_decode': None, 'cuda_graph_max_bs_prefill': None, 'cuda_graph_bs_decode': None, 'cuda_graph_bs_prefill': None, 'cuda_graph_prefill_max_context': None, 'disable_prefill_cuda_graph': False, 'disable_decode_cuda_graph': False, 'disable_cuda_graph': False, 'disable_cuda_graph_padding': False, 'enable_profile_cuda_graph': False, 'enable_cudagraph_gc': False, 'debug_cuda_graph': False, 'enable_layerwise_nvtx_marker': False, 'enable_nccl_nvls': False, 'enable_symm_mem': False, 'triton_attention_reduce_in_fp32': False, 'triton_attention_num_kv_splits': 8, 'triton_attention_split_tile_size': None, 'flashinfer_mla_disable_ragged': False, 'enable_fused_qk_norm_rope': False, 'enable_precise_embedding_interpolation': False, 'enable_fused_moe_sum_all_reduce': False, 'enable_deepseek_v4_fp4_indexer': False, 'disable_custom_all_reduce': False, 'enable_mscclpp': False, 'enable_torch_symm_mem': False, 'enable_scattered_sconv': False, 'pre_warm_nccl': False, 'boundary_reduction': 'rs+rsv', 'enable_quant_communications': False, 'enable_flashinfer_allreduce_fusion': False, 'enforce_disable_flashinfer_allreduce_fusion': False, 'flashinfer_allreduce_fusion_backend': None, 'enable_aiter_allreduce_fusion': False, 'enable_torch_compile': False, 'enable_torch_compile_debug_mode': False, 'torch_compile_max_bs': 32, 'speculative_algorithm': None, 'uno_lora_path': None, 'speculative_draft_model_path': None, 'speculative_draft_model_revision': None, 'speculative_draft_load_format': None, 'speculative_num_steps': None, 'speculative_eagle_topk': None, 'speculative_num_draft_tokens': None, 'speculative_dflash_block_size': None, 'speculative_dspark_block_size': None, 'speculative_dspark_sps_table_path': None, 'speculative_dspark_confidence_sts_path': None, 'speculative_dspark_align_verify_tokens_to_graph_tier': False, 'speculative_accept_threshold_single': 1.0, 'speculative_accept_threshold_acc': 1.0, 'speculative_use_rejection_sampling': False, 'speculative_token_map': None, 'speculative_attention_mode': 'prefill', 'speculative_draft_attention_backend': None, 'speculative_dsa_topk_backend': 'sgl-kernel', 'speculative_draft_kv_cache_dtype': None, 'speculative_draft_window_size': None, 'speculative_moe_runner_backend': 'auto', 'speculative_moe_a2a_backend': None, 'speculative_enable_w4a4_mxfp4_megamoe': None, 'speculative_draft_model_quantization': None, '_speculative_draft_quantization_explicitly_set': False, 'speculative_skip_dp_mlp_sync': False, 'enable_multi_layer_eagle': False, 'speculative_adaptive': False, 'speculative_adaptive_config': None, 'decoupled_spec_bind_endpoint': None, 'decoupled_spec_connect_endpoints': None, 'decoupled_spec_rank': None, 'decoupled_spec_role': 'null', 'spec_trace_dir': None, 'speculative_ngram_min_bfs_breadth': 1, 'speculative_ngram_max_bfs_breadth': 10, 'speculative_ngram_match_type': 'BFS', 'speculative_ngram_max_trie_depth': 18, 'speculative_ngram_capacity': 10000000, 'speculative_ngram_external_corpus_path': None, 'speculative_ngram_external_sam_budget': 0, 'speculative_ngram_external_corpus_max_tokens': 10000000, 'ep_size': 1, 'moe_a2a_backend': 'none', 'enable_w4a4_mxfp4_megamoe': False, 'deepep_v2_mode': 'direct', 'moe_runner_backend': 'auto', 'flashinfer_mxfp4_moe_precision': 'default', 'deepep_mode': 'auto', 'fuseep_mode': 2, 'deepep_dispatcher_output_dtype': 'auto', 'ep_num_redundant_experts': 0, 'ep_dispatch_algorithm': None, 'init_expert_location': 'trivial', 'enable_eplb': False, 'eplb_algorithm': 'auto', 'eplb_rebalance_num_iterations': 1000, 'eplb_rebalance_layers_per_chunk': None, 'eplb_min_rebalancing_utilization_threshold': 1.0, 'expert_distribution_recorder_mode': None, 'expert_distribution_recorder_buffer_size': 1000, 'expert_balancedness_report_mode': 'off', 'deepep_config': None, 'moe_dense_tp_size': None, 'elastic_ep_backend': None, 'enable_elastic_expert_backup': False, 'mooncake_ib_device': None, 'enable_waterfill': False, 'ep_join_mode': None, 'ep_join_rank_offset': 0, 'elastic_ep_initial_size': None, 'max_ep_size': None, 'elastic_ep_scale_timeout': 600, 'disable_flashinfer_cutlass_moe_fp4_allgather': False, 'disable_shared_experts_fusion': False, 'enforce_shared_experts_fusion': False, 'max_mamba_cache_size': None, 'mamba_ssm_dtype': None, 'mamba_max_states_per_path': -1, 'enable_mamba_cache_stochastic_rounding': False, 'mamba_cache_philox_rounds': 0, 'mamba_full_memory_ratio': 0.9, 'mamba_radix_cache_strategy': 'auto', 'uses_mamba_radix_cache': False, 'mamba_track_interval': 256, 'enable_int8_mamba_checkpoint': False, 'int8_mamba_ckpt_size': None, 'linear_attn_backend': 'triton', 'linear_attn_decode_backend': None, 'linear_attn_prefill_backend': None, 'linear_attn_verify_backend': None, 'enable_linear_replayssm': False, 'linear_replayssm_cache_len': 16, 'enable_linear_replayssm_spec': False, 'enable_hierarchical_cache': False, 'hicache_host_memory_mode': 'cache', 'hicache_ratio': 2.0, 'hicache_size': 0, 'hicache_write_policy': 'write_through', 'hicache_io_backend': 'kernel', 'hicache_mem_layout': 'page_first', 'hicache_storage_backend': None, 'hicache_storage_prefetch_policy': 'timeout', 'hicache_storage_backend_extra_config': None, 'hicache_storage_prefetch_retry_poll_interval': 8, 'hicache_storage_prefetch_retry_max_attempts': 8, 'enable_unified_cache_external_linker': False, 'unified_cache_external_linker_backend': 'mooncake', 'enable_hisparse': False, 'hisparse_config': None, 'enable_broadcast_mm_inputs_process': False, 'enable_prefix_mm_cache': False, 'mm_enable_dp_encoder': False, 'mm_process_config': {}, 'mm_processor_worker_num': 0, 'mm_io_worker_num': 0, 'allowed_media_domains': [], 'media_url_max_file_size_mb': 64, 'mm_preprocess_cache_size_mb': None, 'trust_mm_content_hashes': False, 'limit_mm_data_per_request': None, 'enable_mm_global_cache': False, 'image_processor_backend': 'auto', 'mm_global_cache_backend': 'mooncake', 'disable_fast_image_processor': False, 'mm_feature_transport': 'cpu', 'enable_lora': None, 'enable_lora_overlap_loading': None, 'max_lora_rank': None, 'lora_target_modules': None, 'lora_paths': None, 'max_loaded_loras': None, 'max_loras_per_batch': 8, 'lora_eviction_policy': 'lru', 'lora_backend': 'csgmv', 'max_lora_chunk_size': 16, 'experts_shared_outer_loras': None, 'lora_use_virtual_experts': False, 'lora_strict_loading': False, 'lora_drain_wait_threshold': 0.0, 'enable_two_batch_overlap': False, 'enable_single_batch_overlap': False, 'tbo_token_distribution_threshold': 0.48, 'cpu_offload_gb': 0, 'offload_group_size': -1, 'offload_num_in_group': 1, 'offload_prefetch_step': 1, 'offload_mode': 'cpu', 'enable_lmcache': False, 'lmcache_config_file': None, 'enable_flexkv': False, 'flexkv_config_file': None, 'kt_weight_path': None, 'kt_method': 'AMXINT4', 'kt_cpuinfer': None, 'kt_threadpool_count': 2, 'kt_num_gpu_experts': None, 'kt_max_deferred_experts_per_token': None, 'dllm_algorithm': None, 'dllm_algorithm_config': None, 'dllm_fdfo': True, 'disaggregation_mode': 'null', 'disaggregation_transfer_backend': 'mooncake', 'disaggregation_bootstrap_port': 8998, 'disaggregation_ib_device': None, 'disaggregation_decode_enable_radix_cache': False, 'disaggregation_decode_enable_offload_kvcache': False, 'disaggregation_decode_retraction_backup': None, 'num_reserved_decode_tokens': 512, 'disaggregation_decode_extra_slots': None, 'disaggregation_decode_polling_interval': 1, 'optimistic_prefill_attempts': 0, 'encoder_only': False, 'language_only': False, 'language_model_only': False, 'encoder_transfer_backend': 'zmq_to_scheduler', 'encoder_urls': [], 'encoder_bootstrap_port': 8997, 'encoder_register_urls': [], 'enable_adaptive_dispatch_to_encoder': False, 'enable_pdmux': False, 'pdmux_config_path': None, 'sm_group_num': 8, 'startup_weight_load_mode': 'serial', 'custom_weight_loader': [], 'weight_loader_disable_mmap': False, 'weight_loader_prefetch_checkpoints': False, 'weight_loader_prefetch_num_threads': 4, 'weight_loader_drop_cache_after_load': False, 'remote_instance_weight_loader_seed_instance_ip': None, 'remote_instance_weight_loader_seed_instance_service_port': None, 'remote_instance_weight_loader_send_weights_group_ports': None, 'remote_instance_weight_loader_backend': 'nccl', 'remote_instance_weight_loader_start_seed_via_transfer_engine': False, 'engine_info_bootstrap_port': 6789, 'modelexpress_config': None, 'download_dir': None, 'model_checksum': None, 'delete_ckpt_after_loading': False, 'decrypted_config_file': None, 'decrypted_draft_config_file': None, 'checkpoint_engine_wait_weights_before_ready': False, 'enable_prefill_delayer': False, 'prefill_delayer_max_delay_passes': 30, 'prefill_delayer_token_usage_low_watermark': None, 'prefill_delayer_forward_passes_buckets': None, 'prefill_delayer_wait_seconds_buckets': None, 'prefill_delayer_queue_min_ratio': None, 'prefill_delayer_max_delay_ms': None, 'min_free_slots_delay': None, 'enable_deterministic_inference': False, 'rl_on_policy_target': None, 'kv_canary': 'none', 'kv_canary_real_data': 'none', 'kv_canary_sweep_interval': 0, 'enable_dynamic_batch_tokenizer': False, 'dynamic_batch_tokenizer_batch_size': 32, 'dynamic_batch_tokenizer_batch_timeout': 0.002, 'enable_tokenizer_batch_encode': False, 'disable_tokenizer_batch_decode': False, 'debug_tensor_dump_output_folder': None, 'debug_tensor_dump_layers': None, 'debug_tensor_dump_input_file': None, 'enable_memory_saver': False, 'enable_weights_cpu_backup': False, 'enable_draft_weights_cpu_backup': False, 'enable_custom_logit_processor': False, 'enable_return_hidden_states': False, 'return_hidden_states_mode': None, 'enable_return_routed_experts': False, 'enable_return_indexer_topk': False, 'sampling_mask_max_tokens': 4096, 'disable_outlines_disk_cache': False, 'enable_mis': False, 'weight_cache_mode': 'off', 'weight_cache_socket': None, 'weight_cache_timeout': 1800, 'forward_hooks': None, 'msprobe_dump_config': None, 'ple_offload_embedding': None, 'ple_offload_backend': 'pinned', 'ple_offload_dir': None, 'disaggregation_enable_kv_checksum': False, 'enable_pd_role_switch': False, 'speculative_domino_candidate_pool_size': 2048, 'flashinfer_a2a_dispatch_type': None, 'cuda_graph_max_seq_len_prefill': None, 'prefill_kv_cache_dequant_dtype': 'auto', 'dsv4_attn_backend': 'auto', 'otlp_service_name': None, '_radix_eviction_policy_explicitly_set': False, 'hicache_host_memory_fraction': 0.8, 'enable_linker_mla_dedup': False, '_swa_full_tokens_ratio_explicitly_set': False, 'swa_prefix_tails': None, 'enable_encoder_swa_bounded_replay': False, 'enable_decoder_swa_bounded_replay': False, 'enable_response_store': False, 'disaggregation_decode_host_receive_threshold': 1.0, 'qsa_indexer_dtype': 'auto', 'disaggregation_decode_allocation_policy': 'early', 'speculative_boundary_reduction': 'rs+rsv', 'speculative_use_block_verification': False, 'speculative_draft_sink_size': None, 'disable_aiter_allreduce_fusion_in_prefill': False, 'disable_aiter_allreduce_fusion_in_decode': False, 'dsa_triton_union': 0, 'enable_dsa_fused_indexer': None, 'enable_cp_tp_group_sharing': False, 'enable_watermark': False, 'watermark_config': '<redacted>', 'watermark_key': '<redacted>', 'watermark_key_b': '<redacted>', 'watermark_context_window': 4, 'watermark_mixing_probability': 0.5, 'watermark_max_probability': 1.0, 'watermark_default_enabled': False, 'watermark_enforce_all': False, 'grpc_response_timeout_secs': 300}
[2026-10-17 14:30:58] Using default HuggingFace chat template with detected content format: string
[2026-10-17 14:31:02] Init parallel begin.
[2026-10-17 14:31:02] Init parallel ends. elapsed=0.26 s
[2026-10-17 14:31:03] Memory baseline taken. mem usage=0.00 GB
/home/rohit/sglang-lab/.venv/lib/python3.12/site-packages/torch/jit/_script.py:1491: FutureWarning: `torch.jit.script` is deprecated. Please switch to `torch.compile` or `torch.export`.
  warnings.warn(
/home/rohit/sglang-lab/.venv/lib/python3.12/site-packages/torch/jit/_script.py:1643: FutureWarning: `torch.jit.interface` is deprecated. Please use `torch.compile` instead.
  warnings.warn(
/home/rohit/sglang-lab/.venv/lib/python3.12/site-packages/torch/jit/_script.py:1491: FutureWarning: `torch.jit.script` is deprecated. Please switch to `torch.compile` or `torch.export`.
  warnings.warn(
[2026-10-17 14:31:04] Load weight begin. avail mem=113.21 GB
[2026-10-17 14:31:06] Found local HF snapshot for Qwen/Qwen3-30B-A3B-Instruct-2507 at /home/rohit/sglang-lab/hf/hub/models--Qwen--Qwen3-30B-A3B-Instruct-2507/snapshots/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe; skipping download.

Multi-thread loading shards:   0% Completed | 0/16 [00:00<?, ?it/s]
Multi-thread loading shards:   6% Completed | 1/16 [00:22<05:33, 22.23s/it]
Multi-thread loading shards:  12% Completed | 2/16 [00:42<04:59, 21.37s/it]
Multi-thread loading shards:  19% Completed | 3/16 [01:03<04:33, 21.03s/it]
Multi-thread loading shards:  25% Completed | 4/16 [01:24<04:11, 20.95s/it]
Multi-thread loading shards:  31% Completed | 5/16 [01:45<03:49, 20.84s/it]
Multi-thread loading shards:  38% Completed | 6/16 [02:05<03:28, 20.84s/it]
Multi-thread loading shards:  44% Completed | 7/16 [02:26<03:07, 20.80s/it]
Multi-thread loading shards:  50% Completed | 8/16 [02:47<02:46, 20.77s/it]
Multi-thread loading shards:  56% Completed | 9/16 [03:08<02:25, 20.78s/it]
Multi-thread loading shards:  62% Completed | 10/16 [03:28<02:04, 20.74s/it]
Multi-thread loading shards:  69% Completed | 11/16 [03:50<01:45, 21.05s/it]
Multi-thread loading shards:  75% Completed | 12/16 [04:11<01:24, 21.05s/it]
Multi-thread loading shards:  81% Completed | 13/16 [04:32<01:02, 20.94s/it]
Multi-thread loading shards:  88% Completed | 14/16 [04:52<00:41, 20.82s/it]
Multi-thread loading shards:  94% Completed | 15/16 [05:13<00:20, 20.74s/it]
Multi-thread loading shards: 100% Completed | 16/16 [05:19<00:00, 16.33s/it]
Multi-thread loading shards: 100% Completed | 16/16 [05:19<00:00, 19.97s/it]
[2026-10-17 14:36:26] Load weight end. elapsed=322.24 s, type=Qwen3MoeForCausalLM, avail mem=58.43 GB, mem usage=54.78 GB.
[2026-10-17 14:36:41] KV Cache is allocated. dtype: torch.bfloat16, #tokens: 258017, K size: 11.81 GB, V size: 11.81 GB
[2026-10-17 14:36:41] Memory pool end. avail mem=31.40 GB
[2026-10-17 14:36:42] Disable prefill CUDA graph because cuda_graph_config resolved prefill.backend='disabled' (e.g. via --cuda-graph-backend-prefill=disabled or auto-disable rules).
[2026-10-17 14:36:42] max_total_num_tokens=258017, chunked_prefill_size=8192, max_prefill_tokens=16384, max_running_requests=2048, context_len=262144, available_gpu_mem=31.20 GB
[2026-10-17 14:36:42] Init Unified Radix Cache. Components: (<ComponentType.FULL: 0>,). Tree Core: RustUnifiedTreeCore
[2026-10-17 14:36:42] Tree cache initialized: source=default impl=UnifiedRadixCache hybrid_swa=False hybrid_ssm=False hicache_attached=False
[2026-10-17 14:36:44] Engine startup timings (s): load_weight=322.24, kv_cache_allocation=2.07, scheduler_e2e=341.39, cuda_graph={prefill=0.00, decode=0.00, target_verify=0.00, draft_prefill=0.00, draft_decode=0.00, draft_extend=0.00}, tokenizer_e2e=346.34
[2026-10-17 14:36:45] INFO:     Started server process [106604]
[2026-10-17 14:36:45] INFO:     Waiting for application startup.
[2026-10-17 14:36:45] Using default chat sampling params from model generation config: {'temperature': 0.7, 'top_k': 20, 'top_p': 0.8}
[2026-10-17 14:36:47] INFO:     Application startup complete.
[2026-10-17 14:36:47] INFO:     Uvicorn running on http://127.0.0.1:30000 (Press CTRL+C to quit)
[2026-10-17 14:36:48] INFO:     127.0.0.1:42248 - "GET /health HTTP/1.1" 503 Service Unavailable
[2026-10-17 14:36:48] INFO:     127.0.0.1:42252 - "GET /model_info HTTP/1.1" 200 OK
[2026-10-17 14:36:50] INFO:     127.0.0.1:42798 - "GET /health HTTP/1.1" 503 Service Unavailable
[2026-10-17 14:36:51] Using default MoE kernel config. Performance might be sub-optimal! Config file not found at /home/rohit/sglang-lab/.venv/lib/python3.12/site-packages/sglang/srt/layers/moe/moe_runner/triton_utils/configs/triton_3_8_0/E=128,N=768,device_name=NVIDIA_GB10.json, you can create them with https://github.com/sgl-project/sglang/tree/main/benchmark/kernels/fused_moe_triton
[2026-10-17 14:36:51] Using default MoE kernel config. Performance might be sub-optimal! Config file not found at /home/rohit/sglang-lab/.venv/lib/python3.12/site-packages/sglang/srt/layers/moe/moe_runner/triton_utils/configs/triton_3_8_0/E=128,N=768,device_name=NVIDIA_GB10_down.json, you can create them with https://github.com/sgl-project/sglang/tree/main/benchmark/kernels/fused_moe_triton
[2026-10-17 14:36:51] Prefill batch, #new-seq: 1, #new-token: 6, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 0.67
[2026-10-17 14:36:51] INFO:     127.0.0.1:42260 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:36:57] INFO:     127.0.0.1:42808 - "POST /freeze_gc HTTP/1.1" 200 OK
[2026-10-17 14:36:57] The server is fired up and ready to roll!
[2026-10-17 14:36:57] Prefill batch, #new-seq: 1, #new-token: 1, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 0.16
[2026-10-17 14:37:00] Prefill batch, #new-seq: 1, #new-token: 1, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 0.44
[2026-10-17 14:37:01] INFO:     127.0.0.1:51872 - "GET /health HTTP/1.1" 200 OK
/home/rohit/sglang-lab/.venv/lib/python3.12/site-packages/sglang/srt/entrypoints/http_server.py:476: FastAPIDeprecationWarning: ORJSONResponse is deprecated, FastAPI now serializes data directly to JSON bytes via Pydantic when a return type or response model is set, which is faster and doesn't need a custom response class. Read more in the FastAPI docs: https://fastapi.tiangolo.com/advanced/custom-response/#orjson-or-response-model and https://fastapi.tiangolo.com/tutorial/response-model/
  return await original_handler(ORJSONRequest(request.scope, request.receive))
[2026-10-17 14:37:06] INFO:     127.0.0.1:51882 - "GET /v1/models HTTP/1.1" 200 OK
[2026-10-17 14:37:06] INFO:     127.0.0.1:51898 - "GET /v1/models HTTP/1.1" 200 OK
[2026-10-17 14:37:07] INFO:     127.0.0.1:51904 - "GET /model_info HTTP/1.1" 200 OK
[2026-10-17 14:37:11] INFO:     127.0.0.1:41608 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:11] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 43.73
[2026-10-17 14:37:13] INFO:     127.0.0.1:41612 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:13] Prefill batch, #new-seq: 1, #new-token: 1, #cached-token: 511, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 0.49
[2026-10-17 14:37:14] Decode batch, #running-req: 1, #token: 515, token usage: 0.00, cuda graph: False, gen throughput (token/s): 1.27, #queue-req: 0
[2026-10-17 14:37:15] Decode batch, #running-req: 1, #token: 555, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.74, #queue-req: 0
[2026-10-17 14:37:16] Decode batch, #running-req: 1, #token: 595, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.67, #queue-req: 0
[2026-10-17 14:37:17] Decode batch, #running-req: 1, #token: 635, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.72, #queue-req: 0
[2026-10-17 14:37:17] INFO:     127.0.0.1:41622 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:18] Prefill batch, #new-seq: 1, #new-token: 256, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 62.69
[2026-10-17 14:37:19] Decode batch, #running-req: 1, #token: 292, token usage: 0.00, cuda graph: False, gen throughput (token/s): 30.14, #queue-req: 0
[2026-10-17 14:37:20] Decode batch, #running-req: 1, #token: 332, token usage: 0.00, cuda graph: False, gen throughput (token/s): 32.20, #queue-req: 0
[2026-10-17 14:37:21] Decode batch, #running-req: 1, #token: 372, token usage: 0.00, cuda graph: False, gen throughput (token/s): 32.08, #queue-req: 0
[2026-10-17 14:37:22] INFO:     127.0.0.1:45690 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:22] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 121.55
[2026-10-17 14:37:23] Decode batch, #running-req: 1, #token: 541, token usage: 0.00, cuda graph: False, gen throughput (token/s): 26.43, #queue-req: 0
[2026-10-17 14:37:24] Decode batch, #running-req: 1, #token: 581, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.81, #queue-req: 0
[2026-10-17 14:37:25] Decode batch, #running-req: 1, #token: 621, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.81, #queue-req: 0
[2026-10-17 14:37:26] INFO:     127.0.0.1:45706 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:26] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 125.48
[2026-10-17 14:37:27] Decode batch, #running-req: 1, #token: 534, token usage: 0.00, cuda graph: False, gen throughput (token/s): 29.64, #queue-req: 0
[2026-10-17 14:37:28] Decode batch, #running-req: 1, #token: 574, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.84, #queue-req: 0
[2026-10-17 14:37:29] Decode batch, #running-req: 1, #token: 614, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.77, #queue-req: 0
[2026-10-17 14:37:30] INFO:     127.0.0.1:59636 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:30] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 118.82
[2026-10-17 14:37:31] Decode batch, #running-req: 1, #token: 527, token usage: 0.00, cuda graph: False, gen throughput (token/s): 25.46, #queue-req: 0
[2026-10-17 14:37:32] Decode batch, #running-req: 1, #token: 567, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.82, #queue-req: 0
[2026-10-17 14:37:33] Decode batch, #running-req: 1, #token: 607, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.78, #queue-req: 0
[2026-10-17 14:37:34] INFO:     127.0.0.1:59640 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:34] Prefill batch, #new-seq: 1, #new-token: 511, #cached-token: 1, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 119.89
[2026-10-17 14:37:35] Decode batch, #running-req: 1, #token: 520, token usage: 0.00, cuda graph: False, gen throughput (token/s): 26.22, #queue-req: 0
[2026-10-17 14:37:36] Decode batch, #running-req: 1, #token: 560, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.77, #queue-req: 0
[2026-10-17 14:37:37] Decode batch, #running-req: 1, #token: 600, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.77, #queue-req: 0
[2026-10-17 14:37:38] Decode batch, #running-req: 1, #token: 0, token usage: 0.00, cuda graph: False, gen throughput (token/s): 32.15, #queue-req: 0
[2026-10-17 14:37:38] INFO:     127.0.0.1:59650 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:39] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 116.48
[2026-10-17 14:37:40] Decode batch, #running-req: 1, #token: 553, token usage: 0.00, cuda graph: False, gen throughput (token/s): 23.95, #queue-req: 0
[2026-10-17 14:37:41] Decode batch, #running-req: 1, #token: 593, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.76, #queue-req: 0
[2026-10-17 14:37:43] Decode batch, #running-req: 1, #token: 633, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.73, #queue-req: 0
[2026-10-17 14:37:43] INFO:     127.0.0.1:44900 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:43] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 122.48
[2026-10-17 14:37:44] Decode batch, #running-req: 1, #token: 546, token usage: 0.00, cuda graph: False, gen throughput (token/s): 27.75, #queue-req: 0
[2026-10-17 14:37:45] Decode batch, #running-req: 1, #token: 586, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.91, #queue-req: 0
[2026-10-17 14:37:47] Decode batch, #running-req: 1, #token: 626, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.83, #queue-req: 0
[2026-10-17 14:37:47] INFO:     127.0.0.1:44908 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:47] Prefill batch, #new-seq: 1, #new-token: 496, #cached-token: 1, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 116.57
[2026-10-17 14:37:48] Decode batch, #running-req: 1, #token: 524, token usage: 0.00, cuda graph: False, gen throughput (token/s): 26.21, #queue-req: 0
[2026-10-17 14:37:49] Decode batch, #running-req: 1, #token: 564, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.79, #queue-req: 0
[2026-10-17 14:37:51] Decode batch, #running-req: 1, #token: 604, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.79, #queue-req: 0
[2026-10-17 14:37:51] INFO:     127.0.0.1:45676 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:52] Prefill batch, #new-seq: 1, #new-token: 511, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 118.23
[2026-10-17 14:37:52] Decode batch, #running-req: 1, #token: 531, token usage: 0.00, cuda graph: False, gen throughput (token/s): 25.23, #queue-req: 0
[2026-10-17 14:37:53] Decode batch, #running-req: 1, #token: 571, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.74, #queue-req: 0
[2026-10-17 14:37:55] Decode batch, #running-req: 1, #token: 611, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.78, #queue-req: 0
[2026-10-17 14:37:56] INFO:     127.0.0.1:45682 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:37:56] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 121.02
[2026-10-17 14:37:56] Decode batch, #running-req: 1, #token: 525, token usage: 0.00, cuda graph: False, gen throughput (token/s): 26.78, #queue-req: 0
[2026-10-17 14:37:57] Decode batch, #running-req: 1, #token: 565, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.79, #queue-req: 0
[2026-10-17 14:37:59] Decode batch, #running-req: 1, #token: 605, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.82, #queue-req: 0
[2026-10-17 14:38:00] INFO:     127.0.0.1:33594 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:00] Prefill batch, #new-seq: 1, #new-token: 509, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 118.50
[2026-10-17 14:38:00] Decode batch, #running-req: 1, #token: 515, token usage: 0.00, cuda graph: False, gen throughput (token/s): 25.69, #queue-req: 0
[2026-10-17 14:38:02] Decode batch, #running-req: 1, #token: 555, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.79, #queue-req: 0
[2026-10-17 14:38:03] Decode batch, #running-req: 1, #token: 595, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.76, #queue-req: 0
[2026-10-17 14:38:04] Decode batch, #running-req: 1, #token: 635, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.74, #queue-req: 0
[2026-10-17 14:38:04] INFO:     127.0.0.1:33600 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:04] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 121.29
[2026-10-17 14:38:06] Decode batch, #running-req: 1, #token: 551, token usage: 0.00, cuda graph: False, gen throughput (token/s): 27.03, #queue-req: 0
[2026-10-17 14:38:07] Decode batch, #running-req: 1, #token: 591, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.86, #queue-req: 0
[2026-10-17 14:38:08] Decode batch, #running-req: 1, #token: 631, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.83, #queue-req: 0
[2026-10-17 14:38:08] INFO:     127.0.0.1:33612 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:09] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 118.55
[2026-10-17 14:38:10] Decode batch, #running-req: 1, #token: 544, token usage: 0.00, cuda graph: False, gen throughput (token/s): 25.17, #queue-req: 0
[2026-10-17 14:38:11] Decode batch, #running-req: 1, #token: 584, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.77, #queue-req: 0
[2026-10-17 14:38:12] Decode batch, #running-req: 1, #token: 624, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.66, #queue-req: 0
[2026-10-17 14:38:13] INFO:     127.0.0.1:45908 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:13] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 119.18
[2026-10-17 14:38:14] Decode batch, #running-req: 1, #token: 537, token usage: 0.00, cuda graph: False, gen throughput (token/s): 25.75, #queue-req: 0
[2026-10-17 14:38:15] Decode batch, #running-req: 1, #token: 577, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.73, #queue-req: 0
[2026-10-17 14:38:16] Decode batch, #running-req: 1, #token: 617, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.68, #queue-req: 0
[2026-10-17 14:38:17] INFO:     127.0.0.1:45912 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:17] Prefill batch, #new-seq: 1, #new-token: 511, #cached-token: 1, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 120.32
[2026-10-17 14:38:18] Decode batch, #running-req: 1, #token: 530, token usage: 0.00, cuda graph: False, gen throughput (token/s): 26.54, #queue-req: 0
[2026-10-17 14:38:19] Decode batch, #running-req: 1, #token: 570, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.77, #queue-req: 0
[2026-10-17 14:38:20] Decode batch, #running-req: 1, #token: 610, token usage: 0.00, cuda graph: False, gen throughput (token/s): 31.82, #queue-req: 0
[2026-10-17 14:38:21] INFO:     127.0.0.1:60838 - "GET /server_info HTTP/1.1" 200 OK
[2026-10-17 14:38:21] INFO:     127.0.0.1:60842 - "GET /server_info HTTP/1.1" 200 OK
[2026-10-17 14:38:27] INFO:     127.0.0.1:60858 - "GET /v1/models HTTP/1.1" 200 OK
[2026-10-17 14:38:27] INFO:     127.0.0.1:60866 - "GET /v1/models HTTP/1.1" 200 OK
[2026-10-17 14:38:28] INFO:     127.0.0.1:60868 - "GET /model_info HTTP/1.1" 200 OK
[2026-10-17 14:38:32] INFO:     127.0.0.1:49376 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:32] Prefill batch, #new-seq: 1, #new-token: 1, #cached-token: 511, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 0.07
[2026-10-17 14:38:32] Decode batch, #running-req: 1, #token: 523, token usage: 0.00, cuda graph: False, gen throughput (token/s): 3.43, #queue-req: 0
[2026-10-17 14:38:34] INFO:     127.0.0.1:49382 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:34] INFO:     127.0.0.1:49394 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:34] INFO:     127.0.0.1:49400 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:34] INFO:     127.0.0.1:49414 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:34] INFO:     127.0.0.1:49418 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:34] INFO:     127.0.0.1:49430 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:34] INFO:     127.0.0.1:49440 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:34] INFO:     127.0.0.1:49444 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:34] Prefill batch, #new-seq: 1, #new-token: 1, #cached-token: 511, token usage: 0.01, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 0.49
[2026-10-17 14:38:34] Prefill batch, #new-seq: 7, #new-token: 7, #cached-token: 3321, token usage: 0.01, #running-req: 1, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 86.28
[2026-10-17 14:38:36] Decode batch, #running-req: 8, #token: 3999, token usage: 0.02, cuda graph: False, gen throughput (token/s): 47.41, #queue-req: 0
[2026-10-17 14:38:40] Decode batch, #running-req: 8, #token: 4319, token usage: 0.02, cuda graph: False, gen throughput (token/s): 80.64, #queue-req: 0
[2026-10-17 14:38:44] Decode batch, #running-req: 8, #token: 4639, token usage: 0.02, cuda graph: False, gen throughput (token/s): 79.95, #queue-req: 0
[2026-10-17 14:38:46] INFO:     127.0.0.1:58014 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:46] INFO:     127.0.0.1:58026 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:46] INFO:     127.0.0.1:58036 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:46] INFO:     127.0.0.1:58046 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:46] INFO:     127.0.0.1:58054 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:46] INFO:     127.0.0.1:58070 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:46] INFO:     127.0.0.1:58082 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:46] INFO:     127.0.0.1:58096 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:46] Prefill batch, #new-seq: 1, #new-token: 1, #cached-token: 496, token usage: 0.02, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 0.08
[2026-10-17 14:38:46] Prefill batch, #new-seq: 7, #new-token: 7, #cached-token: 3573, token usage: 0.02, #running-req: 1, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 79.80
[2026-10-17 14:38:48] Decode batch, #running-req: 8, #token: 4180, token usage: 0.02, cuda graph: False, gen throughput (token/s): 80.04, #queue-req: 0
[2026-10-17 14:38:51] Decode batch, #running-req: 8, #token: 4500, token usage: 0.02, cuda graph: False, gen throughput (token/s): 86.49, #queue-req: 0
[2026-10-17 14:38:55] Decode batch, #running-req: 8, #token: 4820, token usage: 0.02, cuda graph: False, gen throughput (token/s): 86.39, #queue-req: 0
[2026-10-17 14:38:58] INFO:     127.0.0.1:42252 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:58] INFO:     127.0.0.1:42254 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:58] INFO:     127.0.0.1:42270 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:58] INFO:     127.0.0.1:42278 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:58] INFO:     127.0.0.1:42286 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:58] INFO:     127.0.0.1:42300 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:58] INFO:     127.0.0.1:42308 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:58] INFO:     127.0.0.1:42316 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:38:59] Prefill batch, #new-seq: 1, #new-token: 511, #cached-token: 1, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 42.32
[2026-10-17 14:38:59] Prefill batch, #new-seq: 7, #new-token: 3553, #cached-token: 2, token usage: 0.02, #running-req: 1, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 4812.06
[2026-10-17 14:39:00] Decode batch, #running-req: 8, #token: 4108, token usage: 0.02, cuda graph: False, gen throughput (token/s): 66.19, #queue-req: 0
[2026-10-17 14:39:03] Decode batch, #running-req: 8, #token: 4428, token usage: 0.02, cuda graph: False, gen throughput (token/s): 84.44, #queue-req: 0
[2026-10-17 14:39:07] Decode batch, #running-req: 8, #token: 4748, token usage: 0.02, cuda graph: False, gen throughput (token/s): 84.92, #queue-req: 0
[2026-10-17 14:39:11] Decode batch, #running-req: 8, #token: 5068, token usage: 0.02, cuda graph: False, gen throughput (token/s): 81.52, #queue-req: 0
[2026-10-17 14:39:11] INFO:     127.0.0.1:42952 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:11] INFO:     127.0.0.1:42960 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:11] INFO:     127.0.0.1:42974 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:11] INFO:     127.0.0.1:42976 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:11] INFO:     127.0.0.1:42984 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:12] INFO:     127.0.0.1:43000 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:12] INFO:     127.0.0.1:43006 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:12] INFO:     127.0.0.1:43020 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:12] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 41.07
[2026-10-17 14:39:12] Prefill batch, #new-seq: 7, #new-token: 3572, #cached-token: 8, token usage: 0.02, #running-req: 1, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 4928.62
[2026-10-17 14:39:16] Decode batch, #running-req: 8, #token: 4389, token usage: 0.02, cuda graph: False, gen throughput (token/s): 61.23, #queue-req: 0
[2026-10-17 14:39:20] Decode batch, #running-req: 8, #token: 4709, token usage: 0.02, cuda graph: False, gen throughput (token/s): 78.07, #queue-req: 0
[2026-10-17 14:39:24] Decode batch, #running-req: 8, #token: 5029, token usage: 0.02, cuda graph: False, gen throughput (token/s): 77.80, #queue-req: 0
[2026-10-17 14:39:26] INFO:     127.0.0.1:58204 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:26] INFO:     127.0.0.1:58220 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:26] INFO:     127.0.0.1:58236 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:26] INFO:     127.0.0.1:58240 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:26] INFO:     127.0.0.1:58248 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:26] INFO:     127.0.0.1:58252 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:26] INFO:     127.0.0.1:58266 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:26] INFO:     127.0.0.1:58272 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:26] Prefill batch, #new-seq: 1, #new-token: 511, #cached-token: 0, token usage: 0.01, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 38.05
[2026-10-17 14:39:26] Prefill batch, #new-seq: 4, #new-token: 2044, #cached-token: 0, token usage: 0.02, #running-req: 1, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 4291.86
[2026-10-17 14:39:27] Prefill batch, #new-seq: 3, #new-token: 1535, #cached-token: 0, token usage: 0.02, #running-req: 5, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 3684.25
[2026-10-17 14:39:30] Decode batch, #running-req: 8, #token: 4330, token usage: 0.02, cuda graph: False, gen throughput (token/s): 61.00, #queue-req: 0
[2026-10-17 14:39:34] Decode batch, #running-req: 8, #token: 4650, token usage: 0.02, cuda graph: False, gen throughput (token/s): 79.10, #queue-req: 0
[2026-10-17 14:39:38] Decode batch, #running-req: 8, #token: 4970, token usage: 0.02, cuda graph: False, gen throughput (token/s): 78.72, #queue-req: 0
[2026-10-17 14:39:40] INFO:     127.0.0.1:58250 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:40] INFO:     127.0.0.1:58256 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:40] INFO:     127.0.0.1:58258 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:40] INFO:     127.0.0.1:58274 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:40] INFO:     127.0.0.1:58286 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:40] INFO:     127.0.0.1:58288 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:40] INFO:     127.0.0.1:58302 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:40] INFO:     127.0.0.1:58312 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:40] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 39.09
[2026-10-17 14:39:40] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.02, #running-req: 1, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 1878.40
[2026-10-17 14:39:41] Prefill batch, #new-seq: 6, #new-token: 3285, #cached-token: 3, token usage: 0.02, #running-req: 2, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 5105.07
[2026-10-17 14:39:43] Decode batch, #running-req: 8, #token: 4496, token usage: 0.02, cuda graph: False, gen throughput (token/s): 61.54, #queue-req: 0
[2026-10-17 14:39:47] Decode batch, #running-req: 8, #token: 4816, token usage: 0.02, cuda graph: False, gen throughput (token/s): 79.77, #queue-req: 0
[2026-10-17 14:39:51] Decode batch, #running-req: 8, #token: 5136, token usage: 0.02, cuda graph: False, gen throughput (token/s): 79.68, #queue-req: 0
[2026-10-17 14:39:54] INFO:     127.0.0.1:53670 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:54] INFO:     127.0.0.1:53680 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:54] INFO:     127.0.0.1:53686 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:54] INFO:     127.0.0.1:53700 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:54] INFO:     127.0.0.1:53712 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:54] INFO:     127.0.0.1:53728 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:54] INFO:     127.0.0.1:53740 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:54] INFO:     127.0.0.1:53756 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:39:54] Prefill batch, #new-seq: 1, #new-token: 512, #cached-token: 0, token usage: 0.01, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 39.50
[2026-10-17 14:39:54] Prefill batch, #new-seq: 3, #new-token: 1534, #cached-token: 1, token usage: 0.02, #running-req: 1, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 3607.04
[2026-10-17 14:39:55] Prefill batch, #new-seq: 4, #new-token: 2042, #cached-token: 2, token usage: 0.02, #running-req: 4, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 4109.28
[2026-10-17 14:39:56] Decode batch, #running-req: 8, #token: 4218, token usage: 0.02, cuda graph: False, gen throughput (token/s): 62.45, #queue-req: 0
[2026-10-17 14:40:00] Decode batch, #running-req: 8, #token: 4538, token usage: 0.02, cuda graph: False, gen throughput (token/s): 79.65, #queue-req: 0
[2026-10-17 14:40:04] Decode batch, #running-req: 8, #token: 4858, token usage: 0.02, cuda graph: False, gen throughput (token/s): 77.07, #queue-req: 0
[2026-10-17 14:40:08] INFO:     127.0.0.1:45108 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:40:08] INFO:     127.0.0.1:45110 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:40:08] INFO:     127.0.0.1:45118 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:40:08] INFO:     127.0.0.1:45124 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:40:08] INFO:     127.0.0.1:45140 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:40:08] INFO:     127.0.0.1:45156 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:40:08] INFO:     127.0.0.1:45172 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:40:08] INFO:     127.0.0.1:45174 - "POST /generate HTTP/1.1" 200 OK
[2026-10-17 14:40:08] Prefill batch, #new-seq: 1, #new-token: 510, #cached-token: 1, token usage: 0.01, #running-req: 0, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 38.43
[2026-10-17 14:40:09] Prefill batch, #new-seq: 6, #new-token: 2880, #cached-token: 3, token usage: 0.02, #running-req: 1, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 4806.36
[2026-10-17 14:40:09] Prefill batch, #new-seq: 1, #new-token: 507, #cached-token: 2, token usage: 0.02, #running-req: 7, #queue-req: 0, #pending-token: 0, cuda graph: False, input throughput (token/s): 1879.54
[2026-10-17 14:40:10] Decode batch, #running-req: 8, #token: 3975, token usage: 0.02, cuda graph: False, gen throughput (token/s): 61.14, #queue-req: 0
[2026-10-17 14:40:13] Decode batch, #running-req: 8, #token: 4295, token usage: 0.02, cuda graph: False, gen throughput (token/s): 87.09, #queue-req: 0
[2026-10-17 14:40:17] Decode batch, #running-req: 8, #token: 4615, token usage: 0.02, cuda graph: False, gen throughput (token/s): 86.60, #queue-req: 0
[2026-10-17 14:40:21] INFO:     127.0.0.1:35630 - "GET /server_info HTTP/1.1" 200 OK
[2026-10-17 14:40:21] INFO:     127.0.0.1:35632 - "GET /server_info HTTP/1.1" 200 OK
[2026-10-17 14:40:22] SIGTERM received. signum=None frame=None. Draining requests and shutting down...
[2026-10-17 14:40:22] Gracefully exiting... Remaining number of requests 0. Remaining requests remaining_rids=[].
[2026-10-17 14:40:22] kill_process_tree called: parent_pid=106604, include_parent=False, pid=106604
[2026-10-17 14:40:23] INFO:     Shutting down
[2026-10-17 14:40:23] INFO:     Waiting for application shutdown.
[2026-10-17 14:40:23] INFO:     Application shutdown complete.
[2026-10-17 14:40:23] INFO:     Finished server process [106604]
[2026-10-17 14:40:23] kill_process_tree called: parent_pid=106604, include_parent=False, pid=106604