vllm - 💡(How to fix) Fix [Bug]: qwen 3.5 model launch get stuck for quite a long time [4 comments, 2 participants]

vllm2026-03-31 20:58:37

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

vllm-project/vllm#38656•Fetched 2026-04-08 01:58:43

View on GitHub

Comments

Participants

Timeline

Reactions

Author

yanan1116

Participants

smoothdvd

yanan1116

Timeline (top)

commented ×4labeled ×1

Fix Action

Fix / Workaround

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

Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 64 On-line CPU(s) list: 0-63 Vendor ID: AuthenticAMD Model name: AMD Ryzen Threadripper PRO 7975WX 32-Cores CPU family: 25 Model: 24 Thread(s) per core: 2 Core(s) per socket: 32 Socket(s): 1 Stepping: 1 CPU(s) scaling MHz: 28% CPU max MHz: 5352.0000 CPU min MHz: 545.0000 BogoMIPS: 7987.34 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc amd_ibpb_ret arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid overflow_recov succor smca fsrm flush_l1d debug_swap Virtualization: AMD-V L1d cache: 1 MiB (32 instances) L1i cache: 1 MiB (32 instances) L2 cache: 32 MiB (32 instances) L3 cache: 128 MiB (4 instances) NUMA node(s): 1 NUMA node0 CPU(s): 0-63 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: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Mitigation; Safe RET 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; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Code Example

==============================
        System Info
==============================
OS                           : Ubuntu 24.04.2 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : 18.1.3 (1ubuntu1)
CMake version                : version 3.28.3
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu128
Is debug build               : False
CUDA used to build PyTorch   : 12.8
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 | packaged by Anaconda, Inc. | (main, Mar 19 2026, 20:20:58) [GCC 14.3.0] (64-bit runtime)
Python platform              : Linux-6.8.0-71-generic-x86_64-with-glibc2.39

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.0.140
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : 
GPU 0: NVIDIA RTX 6000 Ada Generation
GPU 1: NVIDIA RTX 6000 Ada Generation

Nvidia driver version        : 550.144.03
cuDNN version                : Could not collect
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        52 bits physical, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               64
On-line CPU(s) list:                  0-63
Vendor ID:                            AuthenticAMD
Model name:                           AMD Ryzen Threadripper PRO 7975WX 32-Cores
CPU family:                           25
Model:                                24
Thread(s) per core:                   2
Core(s) per socket:                   32
Socket(s):                            1
Stepping:                             1
CPU(s) scaling MHz:                   28%
CPU max MHz:                          5352.0000
CPU min MHz:                          545.0000
BogoMIPS:                             7987.34
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc amd_ibpb_ret arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid overflow_recov succor smca fsrm flush_l1d debug_swap
Virtualization:                       AMD-V
L1d cache:                            1 MiB (32 instances)
L1i cache:                            1 MiB (32 instances)
L2 cache:                             32 MiB (32 instances)
L3 cache:                             128 MiB (4 instances)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-63
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: Not affected
Vulnerability Retbleed:               Not affected
Vulnerability Spec rstack overflow:   Mitigation; Safe RET
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; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.6
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-cufile-cu12==1.13.1.3
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cutlass-dsl==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pyzmq==27.1.0
[pip3] torch==2.10.0
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0
[pip3] torchvision==0.25.0
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] flashinfer-python                           0.6.6            pypi_0           pypi
[conda] numpy                                       2.2.6            pypi_0           pypi
[conda] nvidia-cublas-cu12                          12.8.4.1         pypi_0           pypi
[conda] nvidia-cuda-cupti-cu12                      12.8.90          pypi_0           pypi
[conda] nvidia-cuda-nvrtc-cu12                      12.8.93          pypi_0           pypi
[conda] nvidia-cuda-runtime-cu12                    12.8.90          pypi_0           pypi
[conda] nvidia-cudnn-cu12                           9.10.2.21        pypi_0           pypi
[conda] nvidia-cudnn-frontend                       1.18.0           pypi_0           pypi
[conda] nvidia-cufft-cu12                           11.3.3.83        pypi_0           pypi
[conda] nvidia-cufile-cu12                          1.13.1.3         pypi_0           pypi
[conda] nvidia-curand-cu12                          10.3.9.90        pypi_0           pypi
[conda] nvidia-cusolver-cu12                        11.7.3.90        pypi_0           pypi
[conda] nvidia-cusparse-cu12                        12.5.8.93        pypi_0           pypi
[conda] nvidia-cusparselt-cu12                      0.7.1            pypi_0           pypi
[conda] nvidia-cutlass-dsl                          4.4.2            pypi_0           pypi
[conda] nvidia-cutlass-dsl-libs-base                4.4.2            pypi_0           pypi
[conda] nvidia-ml-py                                13.595.45        pypi_0           pypi
[conda] nvidia-nccl-cu12                            2.27.5           pypi_0           pypi
[conda] nvidia-nvjitlink-cu12                       12.8.93          pypi_0           pypi
[conda] nvidia-nvshmem-cu12                         3.4.5            pypi_0           pypi
[conda] nvidia-nvtx-cu12                            12.8.90          pypi_0           pypi
[conda] pyzmq                                       27.1.0           pypi_0           pypi
[conda] torch                                       2.10.0           pypi_0           pypi
[conda] torch-c-dlpack-ext                          0.1.5            pypi_0           pypi
[conda] torchaudio                                  2.10.0           pypi_0           pypi
[conda] torchvision                                 0.25.0           pypi_0           pypi
[conda] transformers                                4.57.6           pypi_0           pypi
[conda] triton                                      3.6.0            pypi_0           pypi

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.1
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      SYS     0-63    0               N/A
GPU1    SYS      X      0-63    0               N/A

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

==============================
     Environment Variables
==============================
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_yanan
LD_LIBRARY_PATH=/home/yanan/miniconda3/envs/vllm/lib/python3.12/site-packages/cv2/../../lib64:
VLLM_WORKER_MULTIPROC_METHOD=spawn

---

vllm serve Qwen/Qwen3.5-35B-A3B-FP8 \
  --api-key "yyy" --port 1703 --gpu_memory_utilization 0.95 --tensor-parallel-size 2 \
  --enable-expert-parallel \
  --language-model-only \
  --reasoning-parser qwen3 \
  --enable-prefix-caching

---

(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297] 
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297]        █     █     █▄   ▄█
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.18.1
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297]   █▄█▀ █     █     █     █  model   Qwen/Qwen3.5-35B-A3B-FP8
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297] 
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:233] non-default args: {'model_tag': 'Qwen/Qwen3.5-35B-A3B-FP8', 'port': 1703, 'api_key': ['yyy'], 'model': 'Qwen/Qwen3.5-35B-A3B-FP8', 'reasoning_parser': 'qwen3', 'tensor_parallel_size': 2, 'enable_expert_parallel': True, 'gpu_memory_utilization': 0.95, 'enable_prefix_caching': True, 'language_model_only': True}
config.json: 20.5kB [00:00, 130MB/s]
preprocessor_config.json: 100%|███████████████████| 390/390 [00:00<00:00, 6.87MB/s]
(APIServer pid=375768) INFO 03-31 16:41:11 [model.py:533] Resolved architecture: Qwen3_5MoeForConditionalGeneration
(APIServer pid=375768) INFO 03-31 16:41:11 [model.py:1582] Using max model len 262144
(APIServer pid=375768) INFO 03-31 16:41:11 [scheduler.py:231] Chunked prefill is enabled with max_num_batched_tokens=2048.
(APIServer pid=375768) WARNING 03-31 16:41:11 [config.py:372] Mamba cache mode is set to 'align' for Qwen3_5MoeForConditionalGeneration by default when prefix caching is enabled
(APIServer pid=375768) INFO 03-31 16:41:11 [config.py:392] Warning: Prefix caching in Mamba cache 'align' mode is currently enabled. Its support for Mamba layers is experimental. Please report any issues you may observe.
(APIServer pid=375768) INFO 03-31 16:41:11 [config.py:212] Setting attention block size to 1056 tokens to ensure that attention page size is >= mamba page size.
(APIServer pid=375768) INFO 03-31 16:41:11 [config.py:243] Padding mamba page size by 0.76% to ensure that mamba page size and attention page size are exactly equal.
(APIServer pid=375768) INFO 03-31 16:41:11 [vllm.py:775] Asynchronous scheduling is enabled.
(APIServer pid=375768) INFO 03-31 16:41:11 [compilation.py:289] Enabled custom fusions: norm_quant, act_quant
tokenizer_config.json: 16.7kB [00:00, 119MB/s]
vocab.json: 6.72MB [00:00, 10.7MB/s]
merges.txt: 3.35MB [00:00, 10.3MB/s]
tokenizer.json: 100%|█████████████████████████| 12.8M/12.8M [00:02<00:00, 5.77MB/s]
chat_template.jinja: 7.76kB [00:00, 31.2MB/s]
(APIServer pid=375768) INFO 03-31 16:41:16 [registry.py:126] All limits of multimodal modalities supported by the model are set to 0, running in text-only mode.
generation_config.json: 100%|█████████████████████| 244/244 [00:00<00:00, 5.75MB/s]
(EngineCore pid=376413) INFO 03-31 16:41:21 [core.py:103] Initializing a V1 LLM engine (v0.18.1) with config: model='Qwen/Qwen3.5-35B-A3B-FP8', speculative_config=None, tokenizer='Qwen/Qwen3.5-35B-A3B-FP8', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=262144, download_dir=None, load_format=auto, tensor_parallel_size=2, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=False, quantization=fp8, enforce_eager=False, 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=Qwen/Qwen3.5-35B-A3B-FP8, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+quant_fp8', 'none', '+quant_fp8'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 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, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], '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': 512, '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=376413) WARNING 03-31 16:41:21 [multiproc_executor.py:997] Reducing Torch parallelism from 32 threads to 1 to avoid unnecessary CPU contention. Set OMP_NUM_THREADS in the external environment to tune this value as needed.
(EngineCore pid=376413) INFO 03-31 16:41:21 [multiproc_executor.py:134] DP group leader: node_rank=0, node_rank_within_dp=0, master_addr=127.0.0.1, mq_connect_ip=10.225.68.16 (local), world_size=2, local_world_size=2
INFO 03-31 16:41:26 [registry.py:126] All limits of multimodal modalities supported by the model are set to 0, running in text-only mode.
(Worker pid=376639) INFO 03-31 16:41:26 [parallel_state.py:1395] world_size=2 rank=0 local_rank=0 distributed_init_method=tcp://127.0.0.1:51271 backend=nccl
INFO 03-31 16:41:26 [registry.py:126] All limits of multimodal modalities supported by the model are set to 0, running in text-only mode.
(Worker pid=376640) INFO 03-31 16:41:26 [parallel_state.py:1395] world_size=2 rank=1 local_rank=1 distributed_init_method=tcp://127.0.0.1:51271 backend=nccl
(Worker pid=376640) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
(Worker pid=376640) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead.
(Worker pid=376639) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
(Worker pid=376639) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead.
(Worker pid=376639) INFO 03-31 16:41:26 [pynccl.py:111] vLLM is using nccl==2.27.5

RAW_BUFFERClick to expand / collapse

Your current environment

==============================
        System Info
==============================
OS                           : Ubuntu 24.04.2 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : 18.1.3 (1ubuntu1)
CMake version                : version 3.28.3
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu128
Is debug build               : False
CUDA used to build PyTorch   : 12.8
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 | packaged by Anaconda, Inc. | (main, Mar 19 2026, 20:20:58) [GCC 14.3.0] (64-bit runtime)
Python platform              : Linux-6.8.0-71-generic-x86_64-with-glibc2.39

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.0.140
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : 
GPU 0: NVIDIA RTX 6000 Ada Generation
GPU 1: NVIDIA RTX 6000 Ada Generation

Nvidia driver version        : 550.144.03
cuDNN version                : Could not collect
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        52 bits physical, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               64
On-line CPU(s) list:                  0-63
Vendor ID:                            AuthenticAMD
Model name:                           AMD Ryzen Threadripper PRO 7975WX 32-Cores
CPU family:                           25
Model:                                24
Thread(s) per core:                   2
Core(s) per socket:                   32
Socket(s):                            1
Stepping:                             1
CPU(s) scaling MHz:                   28%
CPU max MHz:                          5352.0000
CPU min MHz:                          545.0000
BogoMIPS:                             7987.34
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc amd_ibpb_ret arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid overflow_recov succor smca fsrm flush_l1d debug_swap
Virtualization:                       AMD-V
L1d cache:                            1 MiB (32 instances)
L1i cache:                            1 MiB (32 instances)
L2 cache:                             32 MiB (32 instances)
L3 cache:                             128 MiB (4 instances)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-63
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: Not affected
Vulnerability Retbleed:               Not affected
Vulnerability Spec rstack overflow:   Mitigation; Safe RET
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; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.6
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-cufile-cu12==1.13.1.3
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cutlass-dsl==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pyzmq==27.1.0
[pip3] torch==2.10.0
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0
[pip3] torchvision==0.25.0
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] flashinfer-python                           0.6.6            pypi_0           pypi
[conda] numpy                                       2.2.6            pypi_0           pypi
[conda] nvidia-cublas-cu12                          12.8.4.1         pypi_0           pypi
[conda] nvidia-cuda-cupti-cu12                      12.8.90          pypi_0           pypi
[conda] nvidia-cuda-nvrtc-cu12                      12.8.93          pypi_0           pypi
[conda] nvidia-cuda-runtime-cu12                    12.8.90          pypi_0           pypi
[conda] nvidia-cudnn-cu12                           9.10.2.21        pypi_0           pypi
[conda] nvidia-cudnn-frontend                       1.18.0           pypi_0           pypi
[conda] nvidia-cufft-cu12                           11.3.3.83        pypi_0           pypi
[conda] nvidia-cufile-cu12                          1.13.1.3         pypi_0           pypi
[conda] nvidia-curand-cu12                          10.3.9.90        pypi_0           pypi
[conda] nvidia-cusolver-cu12                        11.7.3.90        pypi_0           pypi
[conda] nvidia-cusparse-cu12                        12.5.8.93        pypi_0           pypi
[conda] nvidia-cusparselt-cu12                      0.7.1            pypi_0           pypi
[conda] nvidia-cutlass-dsl                          4.4.2            pypi_0           pypi
[conda] nvidia-cutlass-dsl-libs-base                4.4.2            pypi_0           pypi
[conda] nvidia-ml-py                                13.595.45        pypi_0           pypi
[conda] nvidia-nccl-cu12                            2.27.5           pypi_0           pypi
[conda] nvidia-nvjitlink-cu12                       12.8.93          pypi_0           pypi
[conda] nvidia-nvshmem-cu12                         3.4.5            pypi_0           pypi
[conda] nvidia-nvtx-cu12                            12.8.90          pypi_0           pypi
[conda] pyzmq                                       27.1.0           pypi_0           pypi
[conda] torch                                       2.10.0           pypi_0           pypi
[conda] torch-c-dlpack-ext                          0.1.5            pypi_0           pypi
[conda] torchaudio                                  2.10.0           pypi_0           pypi
[conda] torchvision                                 0.25.0           pypi_0           pypi
[conda] transformers                                4.57.6           pypi_0           pypi
[conda] triton                                      3.6.0            pypi_0           pypi

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.1
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      SYS     0-63    0               N/A
GPU1    SYS      X      0-63    0               N/A

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

==============================
     Environment Variables
==============================
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_yanan
LD_LIBRARY_PATH=/home/yanan/miniconda3/envs/vllm/lib/python3.12/site-packages/cv2/../../lib64:
VLLM_WORKER_MULTIPROC_METHOD=spawn

🐛 Describe the bug

launch cmd:

vllm serve Qwen/Qwen3.5-35B-A3B-FP8 \
  --api-key "yyy" --port 1703 --gpu_memory_utilization 0.95 --tensor-parallel-size 2 \
  --enable-expert-parallel \
  --language-model-only \
  --reasoning-parser qwen3 \
  --enable-prefix-caching

then the gpu utilization goes to 100% and there is no more outputs and logs and it get stuck there.

here is the log , i do not see any issues. it just get stuck

(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297] 
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297]        █     █     █▄   ▄█
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.18.1
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297]   █▄█▀ █     █     █     █  model   Qwen/Qwen3.5-35B-A3B-FP8
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:297] 
(APIServer pid=375768) INFO 03-31 16:41:06 [utils.py:233] non-default args: {'model_tag': 'Qwen/Qwen3.5-35B-A3B-FP8', 'port': 1703, 'api_key': ['yyy'], 'model': 'Qwen/Qwen3.5-35B-A3B-FP8', 'reasoning_parser': 'qwen3', 'tensor_parallel_size': 2, 'enable_expert_parallel': True, 'gpu_memory_utilization': 0.95, 'enable_prefix_caching': True, 'language_model_only': True}
config.json: 20.5kB [00:00, 130MB/s]
preprocessor_config.json: 100%|███████████████████| 390/390 [00:00<00:00, 6.87MB/s]
(APIServer pid=375768) INFO 03-31 16:41:11 [model.py:533] Resolved architecture: Qwen3_5MoeForConditionalGeneration
(APIServer pid=375768) INFO 03-31 16:41:11 [model.py:1582] Using max model len 262144
(APIServer pid=375768) INFO 03-31 16:41:11 [scheduler.py:231] Chunked prefill is enabled with max_num_batched_tokens=2048.
(APIServer pid=375768) WARNING 03-31 16:41:11 [config.py:372] Mamba cache mode is set to 'align' for Qwen3_5MoeForConditionalGeneration by default when prefix caching is enabled
(APIServer pid=375768) INFO 03-31 16:41:11 [config.py:392] Warning: Prefix caching in Mamba cache 'align' mode is currently enabled. Its support for Mamba layers is experimental. Please report any issues you may observe.
(APIServer pid=375768) INFO 03-31 16:41:11 [config.py:212] Setting attention block size to 1056 tokens to ensure that attention page size is >= mamba page size.
(APIServer pid=375768) INFO 03-31 16:41:11 [config.py:243] Padding mamba page size by 0.76% to ensure that mamba page size and attention page size are exactly equal.
(APIServer pid=375768) INFO 03-31 16:41:11 [vllm.py:775] Asynchronous scheduling is enabled.
(APIServer pid=375768) INFO 03-31 16:41:11 [compilation.py:289] Enabled custom fusions: norm_quant, act_quant
tokenizer_config.json: 16.7kB [00:00, 119MB/s]
vocab.json: 6.72MB [00:00, 10.7MB/s]
merges.txt: 3.35MB [00:00, 10.3MB/s]
tokenizer.json: 100%|█████████████████████████| 12.8M/12.8M [00:02<00:00, 5.77MB/s]
chat_template.jinja: 7.76kB [00:00, 31.2MB/s]
(APIServer pid=375768) INFO 03-31 16:41:16 [registry.py:126] All limits of multimodal modalities supported by the model are set to 0, running in text-only mode.
generation_config.json: 100%|█████████████████████| 244/244 [00:00<00:00, 5.75MB/s]
(EngineCore pid=376413) INFO 03-31 16:41:21 [core.py:103] Initializing a V1 LLM engine (v0.18.1) with config: model='Qwen/Qwen3.5-35B-A3B-FP8', speculative_config=None, tokenizer='Qwen/Qwen3.5-35B-A3B-FP8', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=262144, download_dir=None, load_format=auto, tensor_parallel_size=2, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=False, quantization=fp8, enforce_eager=False, 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=Qwen/Qwen3.5-35B-A3B-FP8, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+quant_fp8', 'none', '+quant_fp8'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 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, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], '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': 512, '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=376413) WARNING 03-31 16:41:21 [multiproc_executor.py:997] Reducing Torch parallelism from 32 threads to 1 to avoid unnecessary CPU contention. Set OMP_NUM_THREADS in the external environment to tune this value as needed.
(EngineCore pid=376413) INFO 03-31 16:41:21 [multiproc_executor.py:134] DP group leader: node_rank=0, node_rank_within_dp=0, master_addr=127.0.0.1, mq_connect_ip=10.225.68.16 (local), world_size=2, local_world_size=2
INFO 03-31 16:41:26 [registry.py:126] All limits of multimodal modalities supported by the model are set to 0, running in text-only mode.
(Worker pid=376639) INFO 03-31 16:41:26 [parallel_state.py:1395] world_size=2 rank=0 local_rank=0 distributed_init_method=tcp://127.0.0.1:51271 backend=nccl
INFO 03-31 16:41:26 [registry.py:126] All limits of multimodal modalities supported by the model are set to 0, running in text-only mode.
(Worker pid=376640) INFO 03-31 16:41:26 [parallel_state.py:1395] world_size=2 rank=1 local_rank=1 distributed_init_method=tcp://127.0.0.1:51271 backend=nccl
(Worker pid=376640) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
(Worker pid=376640) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead.
(Worker pid=376639) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
(Worker pid=376639) <frozen importlib._bootstrap_external>:1301: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead.
(Worker pid=376639) INFO 03-31 16:41:26 [pynccl.py:111] vLLM is using nccl==2.27.5

Before submitting a new issue...

Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

extent analysis

TL;DR

The issue is likely related to the high GPU memory utilization causing the process to get stuck, and reducing the --gpu_memory_utilization parameter or increasing the GPU memory may resolve the issue.

Guidance

Check the GPU memory usage and adjust the --gpu_memory_utilization parameter to a lower value, such as 0.8 or 0.9, to prevent the process from consuming too much GPU memory.
Consider increasing the GPU memory or using a more powerful GPU to handle the model's requirements.
Verify that the model is compatible with the current GPU architecture and CUDA version.
Check for any other resource-intensive processes running on the system that may be competing with the vLLM process for resources.

Example

No specific code example is provided, but the launch command can be modified to reduce the GPU memory utilization, for example:

vllm serve Qwen/Qwen3.5-35B-A3B-FP8 \
  --api-key "yyy" --port 1703 --gpu_memory_utilization 0.8 --tensor-parallel-size 2 \
  --enable-expert-parallel \
  --language-model-only \
  --reasoning-parser qwen3 \
  --enable-prefix-caching

Notes

The issue may be specific to the particular model or GPU architecture being used, and further debugging may be required to determine the root cause.

Recommendation

Apply a workaround by reducing the --gpu_memory_utilization parameter to a lower value, such as 0.8 or 0.9, to prevent the process from consuming too much GPU memory.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #tool integration #LLM response #prompt template #environment variable

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

vllm - 💡(How to fix) Fix [Bug]: qwen 3.5 model launch get stuck for quite a long time [4 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

vllm - 💡(How to fix) Fix [Bug]: qwen 3.5 model launch get stuck for quite a long time [4 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING