(APIServer pid=11166) Traceback (most recent call last): (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/bin/vllm", line 6, in <module> (APIServer pid=11166) sys.exit(main()) (APIServer pid=11166) ^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 75, in main (APIServer pid=11166) args.dispatch_function(args) (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 122, in cmd (APIServer pid=11166) uvloop.run(run_server(args)) (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/uvloop/init.py", line 96, in run (APIServer pid=11166) return __asyncio.run( (APIServer pid=11166) ^^^^^^^^^^^^^^ (APIServer pid=11166) File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run (APIServer pid=11166) return runner.run(main) (APIServer pid=11166) ^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run (APIServer pid=11166) return self._loop.run_until_complete(task) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/uvloop/init.py", line 48, in wrapper (APIServer pid=11166) return await main (APIServer pid=11166) ^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 670, in run_server (APIServer pid=11166) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs) (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 684, in run_server_worker (APIServer pid=11166) async with build_async_engine_client( (APIServer pid=11166) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter (APIServer pid=11166) return await anext(self.gen) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 100, in build_async_engine_client (APIServer pid=11166) async with build_async_engine_client_from_engine_args( (APIServer pid=11166) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter (APIServer pid=11166) return await anext(self.gen) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 136, in build_async_engine_client_from_engine_args (APIServer pid=11166) async_llm = AsyncLLM.from_vllm_config( (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/async_llm.py", line 225, in from_vllm_config (APIServer pid=11166) return cls( (APIServer pid=11166) ^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/async_llm.py", line 154, in init (APIServer pid=11166) self.engine_core = EngineCoreClient.make_async_mp_client( (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (APIServer pid=11166) return func(*args, **kwargs) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 130, in make_async_mp_client (APIServer pid=11166) return AsyncMPClient(*client_args) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (APIServer pid=11166) return func(*args, **kwargs) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 887, in init (APIServer pid=11166) super().init( (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 535, in init (APIServer pid=11166) with launch_core_engines( (APIServer pid=11166) File "/usr/lib/python3.12/contextlib.py", line 144, in exit (APIServer pid=11166) next(self.gen) (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 998, in launch_core_engines (APIServer pid=11166) wait_for_engine_startup( (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 1057, in wait_for_engine_startup (APIServer pid=11166) raise RuntimeError( (APIServer pid=11166) RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {} /usr/lib/python3.12/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d '

Fix / Workaround

============================== CPU Info

Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 39 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 32 On-line CPU(s) list: 0-31 Vendor ID: GenuineIntel Model name: Intel(R) Core(TM) i9-14900HX CPU family: 6 Model: 183 Thread(s) per core: 2 Core(s) per socket: 16 Socket(s): 1 Stepping: 1 BogoMIPS: 4838.39 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves avx_vnni vnmi umip waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b fsrm md_clear serialize flush_l1d arch_capabilities Virtualization: VT-x Hypervisor vendor: Microsoft Virtualization type: full L1d cache: 768 KiB (16 instances) L1i cache: 512 KiB (16 instances) L2 cache: 32 MiB (16 instances) L3 cache: 36 MiB (1 instance) NUMA node(s): 1 NUMA node0 CPU(s): 0-31 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Reg file data sampling: Vulnerable: No microcode Vulnerability Retbleed: Mitigation; Enhanced IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Logs / stack trace (APIServer pid=11166) INFO 04-07 11:26:46 [utils.py:299] (APIServer pid=11166) INFO 04-07 11:26:46 [utils.py:299] █ █ █▄ ▄█ (APIServer pid=11166) INFO 04-07 11:26:46 [utils.py:299] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.19.0 (APIServer pid=11166) INFO 04-07 11:26:46 [utils.py:299] █▄█▀ █ █ █ █ model /mnt/d/python/qw3-8b/models/Qwen/Qwen3.5-4B (APIServer pid=11166) INFO 04-07 11:26:46 [utils.py:299] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀ (APIServer pid=11166) INFO 04-07 11:26:46 [utils.py:299] (APIServer pid=11166) INFO 04-07 11:26:46 [utils.py:233] non-default args: {'model_tag': '/mnt/d/python/qw3-8b/models/Qwen/Qwen3.5-4B', 'host': '0.0.0.0', 'model': '/mnt/d/python/qw3-8b/models/Qwen/Qwen3.5-4B', 'max_model_len': 8192, 'enforce_eager': True, 'reasoning_parser': 'qwen3', 'gpu_memory_utilization': 0.88} (APIServer pid=11166) INFO 04-07 11:26:47 [model.py:549] Resolved architecture: Qwen3_5ForConditionalGeneration (APIServer pid=11166) INFO 04-07 11:26:47 [model.py:1678] Using max model len 8192 (APIServer pid=11166) INFO 04-07 11:26:47 [config.py:281] Setting attention block size to 528 tokens to ensure that attention page size is >= mamba page size. (APIServer pid=11166) INFO 04-07 11:26:47 [config.py:312] Padding mamba page size by 0.76% to ensure that mamba page size and attention page size are exactly equal. (APIServer pid=11166) INFO 04-07 11:26:47 [vllm.py:790] Asynchronous scheduling is enabled. (APIServer pid=11166) WARNING 04-07 11:26:47 [vllm.py:848] Enforce eager set, disabling torch.compile and CUDAGraphs. This is equivalent to setting -cc.mode=none -cc.cudagraph_mode=none (APIServer pid=11166) WARNING 04-07 11:26:47 [vllm.py:859] Inductor compilation was disabled by user settings, optimizations settings that are only active during inductor compilation will be ignored. (APIServer pid=11166) INFO 04-07 11:26:47 [vllm.py:1025] Cudagraph is disabled under eager mode (APIServer pid=11166) INFO 04-07 11:26:47 [compilation.py:290] Enabled custom fusions: norm_quant, act_quant (EngineCore pid=11249) INFO 04-07 11:26:56 [core.py:105] Initializing a V1 LLM engine (v0.19.0) with config: model='/mnt/d/python/qw3-8b/models/Qwen/Qwen3.5-4B', speculative_config=None, tokenizer='/mnt/d/python/qw3-8b/models/Qwen/Qwen3.5-4B', 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, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=False, quantization=None, enforce_eager=True, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=/mnt/d/python/qw3-8b/models/Qwen/Qwen3.5-4B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.NONE: 0>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['all'], 'splitting_ops': [], 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_images_per_batch': 0, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'size_asserts': False, 'alignment_asserts': False, 'scalar_asserts': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.NONE: 0>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': True, 'fuse_act_quant': True, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False}, 'max_cudagraph_capture_size': 0, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': True, 'static_all_moe_layers': []} (EngineCore pid=11249) WARNING 04-07 11:26:57 [interface.py:525] Using 'pin_memory=False' as WSL is detected. This may slow down the performance. (EngineCore pid=11249) INFO 04-07 11:26:57 [parallel_state.py:1400] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://172.26.194.97:56397 backend=nccl [W407 11:27:07.164358669 socket.cpp:207] [c10d] The hostname of the client socket cannot be retrieved. err=-3 (EngineCore pid=11249) INFO 04-07 11:27:07 [parallel_state.py:1716] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A, EPLB rank N/A (EngineCore pid=11249) INFO 04-07 11:27:10 [gpu_model_runner.py:4735] Starting to load model /mnt/d/python/qw3-8b/models/Qwen/Qwen3.5-4B... (EngineCore pid=11249) INFO 04-07 11:27:11 [cuda.py:390] Using backend AttentionBackendEnum.FLASH_ATTN for vit attention (EngineCore pid=11249) INFO 04-07 11:27:11 [mm_encoder_attention.py:230] Using AttentionBackendEnum.FLASH_ATTN for MMEncoderAttention. (EngineCore pid=11249) INFO 04-07 11:27:11 [gdn_linear_attn.py:147] Using Triton/FLA GDN prefill kernel (EngineCore pid=11249) INFO 04-07 11:27:11 [cuda.py:334] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION']. (EngineCore pid=11249) INFO 04-07 11:27:11 [flash_attn.py:596] Using FlashAttention version 2 (EngineCore pid=11249) Loading safetensors checkpoint shards: 0% Completed | 0/2 [00:00<?, ?it/s] (EngineCore pid=11249) Loading safetensors checkpoint shards: 50% Completed | 1/2 [00:30<00:30, 30.35s/it] (EngineCore pid=11249) Loading safetensors checkpoint shards: 100% Completed | 2/2 [00:56<00:00, 28.15s/it] (EngineCore pid=11249) Loading safetensors checkpoint shards: 100% Completed | 2/2 [00:56<00:00, 28.48s/it] (EngineCore pid=11249) (EngineCore pid=11249) INFO 04-07 11:28:09 [default_loader.py:384] Loading weights took 58.31 seconds (EngineCore pid=11249) INFO 04-07 11:28:09 [gpu_model_runner.py:4820] Model loading took 8.61 GiB memory and 59.098428 seconds (EngineCore pid=11249) INFO 04-07 11:28:09 [gpu_model_runner.py:5753] Encoder cache will be initialized with a budget of 16384 tokens, and profiled with 1 image items of the maximum feature size. (EngineCore pid=11249) /home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/model_executor/layers/fla/ops/utils.py:113: UserWarning: Input tensor shape suggests potential format mismatch: seq_len (16) < num_heads (32). This may indicate the inputs were passed in head-first format [B, H, T, ...] when head_first=False was specified. Please verify your input tensor format matches the expected shape [B, T, H, ...]. (EngineCore pid=11249) return fn(contiguous_args, contiguous_kwargs) !!!!!!! Segfault encountered !!!!!!! File "<unknown>", line 0, in llvm::SmallVectorBase<unsigned int>::grow_pod(void, unsigned long, unsigned long) File "<unknown>", line 0, in llvm::MachineInstrExpressionTrait::getHashValue(llvm::MachineInstr const const&) File "<unknown>", line 0, in llvm::MachineInstrExpressionTrait::getHashValue(llvm::MachineInstr const const&) File "<unknown>", line 0, in bool llvm::DenseMapBase<llvm::DenseMap<llvm::MachineInstr*, llvm::MachineBasicBlock*, llvm::MachineInstrExpressionTrait, llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*> >, llvm::MachineInstr*, llvm::MachineBasicBlock*, llvm::MachineInstrExpressionTrait, llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*> >::LookupBucketForllvm::MachineInstr*(llvm::MachineInstr* const&, llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*>&) File "<unknown>", line 0, in llvm::DenseMapBase<llvm::DenseMap<llvm::MachineInstr, llvm::MachineBasicBlock*, llvm::MachineInstrExpressionTrait, llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*> >, llvm::MachineInstr*, llvm::MachineBasicBlock*, llvm::MachineInstrExpressionTrait, llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*> >::moveFromOldBuckets(llvm::iterator_range<llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*>>) File "<unknown>", line 0, in llvm::DenseMap<llvm::MachineInstr, llvm::MachineBasicBlock*, llvm::MachineInstrExpressionTrait, llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*> >::grow(unsigned int) File "<unknown>", line 0, in llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*>* llvm::DenseMapBase<llvm::DenseMap<llvm::MachineInstr*, llvm::MachineBasicBlock*, llvm::MachineInstrExpressionTrait, llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*> >, llvm::MachineInstr*, llvm::MachineBasicBlock*, llvm::MachineInstrExpressionTrait, llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*> >::findBucketForInsertionllvm::MachineInstr*(llvm::MachineInstr* const&, llvm::detail::DenseMapPair<llvm::MachineInstr*, llvm::MachineBasicBlock*>) File "<unknown>", line 0, in (anonymous namespace)::MachineCSEImpl::run(llvm::MachineFunction&) File "<unknown>", line 0, in (anonymous namespace)::MachineCSELegacy::runOnMachineFunction(llvm::MachineFunction&) File "<unknown>", line 0, in llvm::MachineFunctionPass::runOnFunction(llvm::Function&) File "<unknown>", line 0, in llvm::FPPassManager::runOnFunction(llvm::Function&) File "<unknown>", line 0, in llvm::FPPassManager::runOnModule(llvm::Module&) File "<unknown>", line 0, in llvm::legacy::PassManagerImpl::run(llvm::Module&) File "/project/python/src/llvm.cc", line 371, in translateLLVMIRToASM(llvm::Module&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::_cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, bool, bool) File "/project/python/src/llvm.cc", line 674, in init_triton_llvm(pybind11::module&&)::$_14::operator()(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > >, bool, bool) const File "/tmp/build-env-3wsfqmws/lib/python3.12/site-packages/pybind11/include/pybind11/cast.h", line 2137, in pybind11::object pybind11::detail::argument_loader<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::_cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > >, bool, bool>::call_impl<pybind11::object, init_triton_llvm(pybind11::module&&)::$14&, 0ul, 1ul, 2ul, 3ul, 4ul, 5ul, 6ul, pybind11::detail::void_type>(init_triton_llvm(pybind11::module&&)::$_14&, std::integer_sequence<unsigned long, 0ul, 1ul, 2ul, 3ul, 4ul, 5ul, 6ul>, pybind11::detail::void_type&&) && File "/tmp/build-env-3wsfqmws/lib/python3.12/site-packages/pybind11/include/pybind11/cast.h", line 2105, in std::enable_if<!std::is_void<pybind11::object>::value, pybind11::object>::type pybind11::detail::argument_loader<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::_cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > >, bool, bool>::call<pybind11::object, pybind11::detail::void_type, init_triton_llvm(pybind11::module&&)::$14&>(init_triton_llvm(pybind11::module&&)::$14&) && File "/tmp/build-env-3wsfqmws/lib/python3.12/site-packages/pybind11/include/pybind11/pybind11.h", line 430, in pybind11::cpp_function::initialize<init_triton_llvm(pybind11::module&&)::$_14, pybind11::object, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::_cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > >, bool, bool, pybind11::name, pybind11::scope, pybind11::sibling, pybind11::return_value_policy>(init_triton_llvm(pybind11::module&&)::$_14&&, pybind11::object ()(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::_cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > >, bool, bool), pybind11::name const&, pybind11::scope const&, pybind11::sibling const&, pybind11::return_value_policy const&)::{lambda(pybind11::detail::function_call&)#1}::operator()(pybind11::detail::function_call&) const File "/tmp/build-env-3wsfqmws/lib/python3.12/site-packages/pybind11/include/pybind11/pybind11.h", line 400, in pybind11::cpp_function::initialize<init_triton_llvm(pybind11::module&&)::$_14, pybind11::object, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::_cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > >, bool, bool, pybind11::name, pybind11::scope, pybind11::sibling, pybind11::return_value_policy>(init_triton_llvm(pybind11::module&&)::$_14&&, pybind11::object ()(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > >, bool, bool), pybind11::name const&, pybind11::scope const&, pybind11::sibling const&, pybind11::return_value_policy const&)::{lambda(pybind11::detail::function_call&)#1}::__invoke(pybind11::detail::function_call&) File "/tmp/build-env-3wsfqmws/lib/python3.12/site-packages/pybind11/include/pybind11/pybind11.h", line 1063, in pybind11::cpp_function::dispatcher(_object, _object*, _object*) File "<unknown>", line 0, in _PyObject_MakeTpCall File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in (anonymous namespace)::THPFunction_apply(_object*, _object*) File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in _PyObject_Call_Prepend File "<unknown>", line 0, in _PyObject_MakeTpCall File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in pybind11::object pybind11::detail::object_apipybind11::handle::operator()<(pybind11::return_value_policy)1, pybind11::detail::args_proxy, pybind11::detail::kwargs_proxy>(pybind11::detail::args_proxy&&, pybind11::detail::kwargs_proxy&&) const File "<unknown>", line 0, in torch::impl::dispatch::PythonKernelHolder::operator()(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocatorc10::IValue >) File "<unknown>", line 0, in c10::Dispatcher::callBoxed(c10::OperatorHandle const&, std::vector<c10::IValue, std::allocatorc10::IValue >) const [clone .isra.0] File "<unknown>", line 0, in torch::jit::invokeOperatorFromPython(c10::ArrayRef<std::shared_ptrtorch::jit::Operator >, pybind11::args const&, pybind11::kwargs const&, std::optionalc10::DispatchKey) File "<unknown>", line 0, in torch::jit::_get_operation_for_overload_or_packet(c10::ArrayRef<std::shared_ptrtorch::jit::Operator >, c10::Symbol, pybind11::args const&, pybind11::kwargs const&, bool, std::optionalc10::DispatchKey) File "<unknown>", line 0, in torch::jit::_get_operation_for_overload_or_packet(std::vector<std::shared_ptrtorch::jit::Operator, std::allocator<std::shared_ptrtorch::jit::Operator > > const&, c10::Symbol, pybind11::args const&, pybind11::kwargs const&, bool, std::optionalc10::DispatchKey) File "<unknown>", line 0, in pybind11::cpp_function::initialize<torch::jit::initJITBindings(_object*)::{lambda(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)#2}::operator()(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const::{lambda(pybind11::args const&, pybind11::kwargs const&)#1}, pybind11::object, pybind11::args const&, pybind11::kwargs const&, pybind11::name, pybind11::doc>(torch::jit::initJITBindings(_object*)::{lambda(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)#2}::operator()(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const::{lambda(pybind11::args const&, pybind11::kwargs const&)#1}&&, pybind11::object ()(pybind11::args const&, pybind11::kwargs const&), pybind11::name const&, pybind11::doc const&)::{lambda(pybind11::detail::function_call&)#1}::_FUN(pybind11::detail::function_call&) File "<unknown>", line 0, in pybind11::cpp_function::dispatcher(_object, _object*, _object*) File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in _PyObject_Call_Prepend File "<unknown>", line 0, in _PyObject_MakeTpCall File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in _PyObject_Call_Prepend File "<unknown>", line 0, in _PyObject_MakeTpCall File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in _PyObject_Call_Prepend File "<unknown>", line 0, in _PyObject_MakeTpCall File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in _PyObject_Call_Prepend File "<unknown>", line 0, in _PyObject_MakeTpCall File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in _PyObject_Call_Prepend File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in _PyObject_Call_Prepend File "<unknown>", line 0, in PyObject_Call File "<unknown>", line 0, in _PyEval_EvalFrameDefault File "<unknown>", line 0, in PyEval_EvalCode File "<unknown>", line 0, in PyRun_StringFlags File "<unknown>", line 0, in PyRun_SimpleStringFlags File "<unknown>", line 0, in Py_RunMain File "<unknown>", line 0, in Py_BytesMain File "<unknown>", line 0, in _start File "<unknown>", line 0, in 0xffffffffffffffff

(APIServer pid=11166) Traceback (most recent call last): (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/bin/vllm", line 6, in <module> (APIServer pid=11166) sys.exit(main()) (APIServer pid=11166) ^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 75, in main (APIServer pid=11166) args.dispatch_function(args) (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 122, in cmd (APIServer pid=11166) uvloop.run(run_server(args)) (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/uvloop/init.py", line 96, in run (APIServer pid=11166) return __asyncio.run( (APIServer pid=11166) ^^^^^^^^^^^^^^ (APIServer pid=11166) File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run (APIServer pid=11166) return runner.run(main) (APIServer pid=11166) ^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run (APIServer pid=11166) return self._loop.run_until_complete(task) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/uvloop/init.py", line 48, in wrapper (APIServer pid=11166) return await main (APIServer pid=11166) ^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 670, in run_server (APIServer pid=11166) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs) (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 684, in run_server_worker (APIServer pid=11166) async with build_async_engine_client( (APIServer pid=11166) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter (APIServer pid=11166) return await anext(self.gen) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 100, in build_async_engine_client (APIServer pid=11166) async with build_async_engine_client_from_engine_args( (APIServer pid=11166) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter (APIServer pid=11166) return await anext(self.gen) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 136, in build_async_engine_client_from_engine_args (APIServer pid=11166) async_llm = AsyncLLM.from_vllm_config( (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/async_llm.py", line 225, in from_vllm_config (APIServer pid=11166) return cls( (APIServer pid=11166) ^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/async_llm.py", line 154, in init (APIServer pid=11166) self.engine_core = EngineCoreClient.make_async_mp_client( (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (APIServer pid=11166) return func(*args, **kwargs) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 130, in make_async_mp_client (APIServer pid=11166) return AsyncMPClient(*client_args) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (APIServer pid=11166) return func(*args, **kwargs) (APIServer pid=11166) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 887, in init (APIServer pid=11166) super().init( (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 535, in init (APIServer pid=11166) with launch_core_engines( (APIServer pid=11166) File "/usr/lib/python3.12/contextlib.py", line 144, in exit (APIServer pid=11166) next(self.gen) (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 998, in launch_core_engines (APIServer pid=11166) wait_for_engine_startup( (APIServer pid=11166) File "/home/cc/venv-vllm-qwen35/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 1057, in wait_for_engine_startup (APIServer pid=11166) raise RuntimeError( (APIServer pid=11166) RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {} /usr/lib/python3.12/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d '