vllm - 💡(How to fix) Fix [Bug]: DeepSeek hangs with overridden num_hidden_layers [1 comments, 1 participants]

vllm2026-03-09 17:42:33

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#36526•Fetched 2026-04-08 00:36:25

View on GitHub

Comments

Participants

Timeline

Reactions

Author

ProExpertProg

Participants

ProExpertProg

Timeline (top)

closed ×1commented ×1labeled ×1

Error Message

Overidding the number of hidden layers is important for debugging DSV3 on a single GPU - while outputs might be wrong, the shapes are right, which is helpful especially for debugging fusion passes (and used in E2E fusion pass testing). When using --hf-overrides.num_hidden_layers=4, Deepseek-v3 fails with the following error:

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): 224 On-line CPU(s) list: 0-223 Vendor ID: GenuineIntel Model name: INTEL(R) XEON(R) PLATINUM 8570 CPU family: 6 Model: 207 Thread(s) per core: 2 Core(s) per socket: 56 Socket(s): 2 Stepping: 2 CPU(s) scaling MHz: 31% CPU max MHz: 4000.0000 CPU min MHz: 800.0000 BogoMIPS: 4200.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 5.3 MiB (112 instances) L1i cache: 3.5 MiB (112 instances) L2 cache: 224 MiB (112 instances) L3 cache: 600 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-55,112-167 NUMA node1 CPU(s): 56-111,168-223 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: 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

Code Example

Collecting environment information...
uv is set
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.3 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04) 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+cu129
Is debug build               : False
CUDA used to build PyTorch   : 12.9
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0] (64-bit runtime)
Python platform              : Linux-6.8.0-85-generic-x86_64-with-glibc2.39

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 13.0.88
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : 
GPU 0: NVIDIA B200
GPU 1: NVIDIA B200
GPU 2: NVIDIA B200
GPU 3: NVIDIA B200
GPU 4: NVIDIA B200
GPU 5: NVIDIA B200
GPU 6: NVIDIA B200
GPU 7: NVIDIA B200

Nvidia driver version        : 580.126.09
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):                               224
On-line CPU(s) list:                  0-223
Vendor ID:                            GenuineIntel
Model name:                           INTEL(R) XEON(R) PLATINUM 8570
CPU family:                           6
Model:                                207
Thread(s) per core:                   2
Core(s) per socket:                   56
Socket(s):                            2
Stepping:                             2
CPU(s) scaling MHz:                   31%
CPU max MHz:                          4000.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4200.00
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            5.3 MiB (112 instances)
L1i cache:                            3.5 MiB (112 instances)
L2 cache:                             224 MiB (112 instances)
L3 cache:                             600 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-55,112-167
NUMA node1 CPU(s):                    56-111,168-223
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:   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

==============================
Versions of relevant libraries
==============================
[pip3] efficientnet-pytorch==0.7.1
[pip3] flashinfer-python==0.6.4
[pip3] mypy-extensions==1.0.0
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.9.1.4
[pip3] nvidia-cuda-cupti-cu12==12.9.79
[pip3] nvidia-cuda-nvrtc-cu12==12.9.86
[pip3] nvidia-cuda-runtime-cu12==12.9.79
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft-cu12==11.4.1.4
[pip3] nvidia-cufile-cu12==1.14.1.1
[pip3] nvidia-curand-cu12==10.3.10.19
[pip3] nvidia-cusolver-cu12==11.7.5.82
[pip3] nvidia-cusparse-cu12==12.5.10.65
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cutlass-dsl==4.4.1
[pip3] nvidia-cutlass-dsl-libs-base==4.4.1
[pip3] nvidia-ml-py==13.590.48
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.9.86
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] open-clip-torch==2.32.0
[pip3] pytorch-lightning==2.5.2
[pip3] pyzmq==27.1.0
[pip3] segmentation-models-pytorch==0.4.0
[pip3] sentence-transformers==5.2.0
[pip3] terratorch==1.0.2
[pip3] torch==2.10.0+cu129
[pip3] torch-c-dlpack-ext==0.1.5
[pip3] torchaudio==2.10.0+cu129
[pip3] torchgeo==0.7.0
[pip3] torchmetrics==1.7.4
[pip3] torchvision==0.25.0+cu129
[pip3] transformers==4.57.5
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.6.0
[pip3] tritonclient==2.64.0
[pip3] vector-quantize-pytorch==1.21.2
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.17.0rc1.dev141+g2347661c4.d20260306 (git sha: 2347661c4, date: 20260306)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    NIC6    NIC7    NIC8    NIC9    NIC10   NIC11   NIC12   NIC13   NIC14   NIC15   CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV18    NV18    NV18    NV18    NV18    NV18    NV18    NODE    NODE    NODE    NODE    PXB     NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-55,112-167    0               N/A
GPU1    NV18     X      NV18    NV18    NV18    NV18    NV18    NV18    NODE    NODE    NODE    NODE    NODE    NODE    NODE    PXB     NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-55,112-167    0               N/A
GPU2    NV18    NV18     X      NV18    NV18    NV18    NV18    NV18    NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE    PXB     NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-55,112-167    0               N/A
GPU3    NV18    NV18    NV18     X      NV18    NV18    NV18    NV18    NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE    PXB     SYS     SYS     SYS     SYS     SYS     SYS     0-55,112-167    0               N/A
GPU4    NV18    NV18    NV18    NV18     X      NV18    NV18    NV18    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PXB     NODE    NODE    NODE    NODE    NODE    56-111,168-223  1               N/A
GPU5    NV18    NV18    NV18    NV18    NV18     X      NV18    NV18    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    PXB     NODE    NODE    56-111,168-223  1               N/A
GPU6    NV18    NV18    NV18    NV18    NV18    NV18     X      NV18    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    PXB     NODE    56-111,168-223  1               N/A
GPU7    NV18    NV18    NV18    NV18    NV18    NV18    NV18     X      SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    PXB     56-111,168-223  1               N/A
NIC0    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS      X      PIX     PIX     PIX     NODE    NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC1    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     PIX      X      PIX     PIX     NODE    NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC2    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     PIX     PIX      X      PIX     NODE    NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC3    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     PIX     PIX     PIX      X      NODE    NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC4    PXB     NODE    NODE    NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE     X      NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC5    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE     X      PIX     NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC6    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    PIX      X      NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC7    NODE    PXB     NODE    NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    NODE    NODE     X      NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC8    NODE    NODE    PXB     NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE     X      NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC9    NODE    NODE    NODE    PXB     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE     X      SYS     SYS     SYS     SYS     SYS     SYS                             
NIC10   SYS     SYS     SYS     SYS     PXB     NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      NODE    NODE    NODE    NODE    NODE                            
NIC11   SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE     X      PIX     NODE    NODE    NODE                            
NIC12   SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    PIX      X      NODE    NODE    NODE                            
NIC13   SYS     SYS     SYS     SYS     NODE    PXB     NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE     X      NODE    NODE                            
NIC14   SYS     SYS     SYS     SYS     NODE    NODE    PXB     NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE     X      NODE                            
NIC15   SYS     SYS     SYS     SYS     NODE    NODE    NODE    PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE     X                              

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

NIC Legend:

  NIC0: mlx5_0
  NIC1: mlx5_1
  NIC2: mlx5_2
  NIC3: mlx5_3
  NIC4: mlx5_4
  NIC5: mlx5_5
  NIC6: mlx5_6
  NIC7: mlx5_7
  NIC8: mlx5_8
  NIC9: mlx5_9
  NIC10: mlx5_10
  NIC11: mlx5_11
  NIC12: mlx5_12
  NIC13: mlx5_13
  NIC14: mlx5_14
  NIC15: mlx5_15

==============================
     Environment Variables
==============================
LD_LIBRARY_PATH=/home/ProExpertProg/git/vllm/.venv/lib/python3.12/site-packages/cv2/../../lib64:/usr/local/cuda-12.9/lib64:/usr/local/cuda-12.9/lib64
CUDA_HOME=/usr/local/cuda-12.9
CUDA_HOME=/usr/local/cuda-12.9
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_ProExpertProg
VLLM_WORKER_MULTIPROC_METHOD=spawn

---

$ vllm serve deepseek-ai/DeepSeek-V3 --hf-overrides.num_hidden_layers=4 --load-format=dummy
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292] 
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292]        █     █     █▄   ▄█
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.17.0rc1.dev141+g2347661c4.d20260306
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292]   █▄█▀ █     █     █     █  model   deepseek-ai/DeepSeek-V3
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292] 
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:228] non-default args: {'model_tag': 'deepseek-ai/DeepSeek-V3', 'model': 'deepseek-ai/DeepSeek-V3', 'hf_overrides': {'num_hidden_layers': 4}, 'load_format': 'dummy'}
(APIServer pid=2260246) INFO 03-09 13:38:04 [model.py:531] Resolved architecture: DeepseekV3ForCausalLM
(APIServer pid=2260246) INFO 03-09 13:38:04 [model.py:1554] Using max model len 163840
(APIServer pid=2260246) INFO 03-09 13:38:04 [scheduler.py:231] Chunked prefill is enabled with max_num_batched_tokens=8192.
(APIServer pid=2260246) INFO 03-09 13:38:04 [vllm.py:754] Asynchronous scheduling is enabled.
(APIServer pid=2260246) INFO 03-09 13:38:04 [compilation.py:286] Enabled custom fusions: norm_quant, act_quant
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:11 [core.py:103] Initializing a V1 LLM engine (v0.17.0rc1.dev141+g2347661c4.d20260306) with config: model='deepseek-ai/DeepSeek-V3', speculative_config=None, tokenizer='deepseek-ai/DeepSeek-V3', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=163840, download_dir=None, load_format=dummy, 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=fp8, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', 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=deepseek-ai/DeepSeek-V3, 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_split_points': [8192], '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_DP0 pid=2260746) INFO 03-09 13:38:12 [parallel_state.py:1395] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://10.14.216.12:59919 backend=nccl
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:12 [parallel_state.py:1717] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank 0, EPLB rank N/A
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [gpu_model_runner.py:4455] Starting to load model deepseek-ai/DeepSeek-V3...
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [cuda.py:317] Using FLASHINFER_MLA attention backend out of potential backends: ['FLASHINFER_MLA', 'CUTLASS_MLA', 'TRITON_MLA'].
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [selector.py:124] Using HND KV cache layout for FLASHINFER_MLA backend.
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [mla_attention.py:2113] Using TRT-LLM ragged DeepSeek prefill for MLA
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [fp8.py:390] Using FLASHINFER_TRTLLM Fp8 MoE backend out of potential backends: ['AITER', 'FLASHINFER_TRTLLM', 'FLASHINFER_CUTLASS', 'DEEPGEMM', 'TRITON', 'MARLIN', 'BATCHED_DEEPGEMM', 'BATCHED_TRITON', 'XPU'].
(EngineCore_DP0 pid=2260746) <frozen importlib._bootstrap_external>:1297: 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.
(EngineCore_DP0 pid=2260746) <frozen importlib._bootstrap_external>:1297: 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.
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [fp8.py:539] Using MoEPrepareAndFinalizeNoDPEPMonolithic
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [gpu_model_runner.py:4538] Model loading took 16.2 GiB memory and 0.499895 seconds
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [interface.py:466] Setting kv cache block size to 32 for FLASHINFER_MLA backend.
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:15 [backends.py:975] Using cache directory: /home/ProExpertProg/.cache/vllm/torch_compile_cache/d6390327fd/rank_0_0/backbone for vLLM's torch.compile
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:15 [backends.py:1035] Dynamo bytecode transform time: 1.54 s
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:16 [backends.py:371] Cache the graph of compile range (1, 8192) for later use
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:17 [backends.py:387] Compiling a graph for compile range (1, 8192) takes 0.80 s
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:17 [decorators.py:606] saved AOT compiled function to /home/ProExpertProg/.cache/vllm/torch_compile_cache/torch_aot_compile/631fac8acbacc2b3373859a29e5c8c10d8dde5d917bea7320b0b0a7f2435d5d4/rank_0_0/model
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:17 [monitor.py:48] torch.compile took 3.27 s in total

---

$ vllm serve qwen/qwen3-30b-a3b --hf-overrides.num_hidden_layers=4 --load-format=dummy
...
(APIServer pid=2265759) INFO:     Application startup complete.

RAW_BUFFERClick to expand / collapse

Your current environment

<details> <summary>The output of <code>python collect_env.py</code></summary>

Collecting environment information...
uv is set
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.3 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04) 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+cu129
Is debug build               : False
CUDA used to build PyTorch   : 12.9
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0] (64-bit runtime)
Python platform              : Linux-6.8.0-85-generic-x86_64-with-glibc2.39

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 13.0.88
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : 
GPU 0: NVIDIA B200
GPU 1: NVIDIA B200
GPU 2: NVIDIA B200
GPU 3: NVIDIA B200
GPU 4: NVIDIA B200
GPU 5: NVIDIA B200
GPU 6: NVIDIA B200
GPU 7: NVIDIA B200

Nvidia driver version        : 580.126.09
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):                               224
On-line CPU(s) list:                  0-223
Vendor ID:                            GenuineIntel
Model name:                           INTEL(R) XEON(R) PLATINUM 8570
CPU family:                           6
Model:                                207
Thread(s) per core:                   2
Core(s) per socket:                   56
Socket(s):                            2
Stepping:                             2
CPU(s) scaling MHz:                   31%
CPU max MHz:                          4000.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4200.00
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            5.3 MiB (112 instances)
L1i cache:                            3.5 MiB (112 instances)
L2 cache:                             224 MiB (112 instances)
L3 cache:                             600 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-55,112-167
NUMA node1 CPU(s):                    56-111,168-223
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:   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

==============================
Versions of relevant libraries
==============================
[pip3] efficientnet-pytorch==0.7.1
[pip3] flashinfer-python==0.6.4
[pip3] mypy-extensions==1.0.0
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.9.1.4
[pip3] nvidia-cuda-cupti-cu12==12.9.79
[pip3] nvidia-cuda-nvrtc-cu12==12.9.86
[pip3] nvidia-cuda-runtime-cu12==12.9.79
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft-cu12==11.4.1.4
[pip3] nvidia-cufile-cu12==1.14.1.1
[pip3] nvidia-curand-cu12==10.3.10.19
[pip3] nvidia-cusolver-cu12==11.7.5.82
[pip3] nvidia-cusparse-cu12==12.5.10.65
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cutlass-dsl==4.4.1
[pip3] nvidia-cutlass-dsl-libs-base==4.4.1
[pip3] nvidia-ml-py==13.590.48
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.9.86
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] open-clip-torch==2.32.0
[pip3] pytorch-lightning==2.5.2
[pip3] pyzmq==27.1.0
[pip3] segmentation-models-pytorch==0.4.0
[pip3] sentence-transformers==5.2.0
[pip3] terratorch==1.0.2
[pip3] torch==2.10.0+cu129
[pip3] torch-c-dlpack-ext==0.1.5
[pip3] torchaudio==2.10.0+cu129
[pip3] torchgeo==0.7.0
[pip3] torchmetrics==1.7.4
[pip3] torchvision==0.25.0+cu129
[pip3] transformers==4.57.5
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.6.0
[pip3] tritonclient==2.64.0
[pip3] vector-quantize-pytorch==1.21.2
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.17.0rc1.dev141+g2347661c4.d20260306 (git sha: 2347661c4, date: 20260306)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    NIC6    NIC7    NIC8    NIC9    NIC10   NIC11   NIC12   NIC13   NIC14   NIC15   CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV18    NV18    NV18    NV18    NV18    NV18    NV18    NODE    NODE    NODE    NODE    PXB     NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-55,112-167    0               N/A
GPU1    NV18     X      NV18    NV18    NV18    NV18    NV18    NV18    NODE    NODE    NODE    NODE    NODE    NODE    NODE    PXB     NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-55,112-167    0               N/A
GPU2    NV18    NV18     X      NV18    NV18    NV18    NV18    NV18    NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE    PXB     NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-55,112-167    0               N/A
GPU3    NV18    NV18    NV18     X      NV18    NV18    NV18    NV18    NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE    PXB     SYS     SYS     SYS     SYS     SYS     SYS     0-55,112-167    0               N/A
GPU4    NV18    NV18    NV18    NV18     X      NV18    NV18    NV18    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     PXB     NODE    NODE    NODE    NODE    NODE    56-111,168-223  1               N/A
GPU5    NV18    NV18    NV18    NV18    NV18     X      NV18    NV18    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    PXB     NODE    NODE    56-111,168-223  1               N/A
GPU6    NV18    NV18    NV18    NV18    NV18    NV18     X      NV18    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    PXB     NODE    56-111,168-223  1               N/A
GPU7    NV18    NV18    NV18    NV18    NV18    NV18    NV18     X      SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    PXB     56-111,168-223  1               N/A
NIC0    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS      X      PIX     PIX     PIX     NODE    NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC1    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     PIX      X      PIX     PIX     NODE    NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC2    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     PIX     PIX      X      PIX     NODE    NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC3    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     PIX     PIX     PIX      X      NODE    NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC4    PXB     NODE    NODE    NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE     X      NODE    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC5    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE     X      PIX     NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC6    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    PIX      X      NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC7    NODE    PXB     NODE    NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    NODE    NODE     X      NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC8    NODE    NODE    PXB     NODE    SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE     X      NODE    SYS     SYS     SYS     SYS     SYS     SYS                             
NIC9    NODE    NODE    NODE    PXB     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE    NODE     X      SYS     SYS     SYS     SYS     SYS     SYS                             
NIC10   SYS     SYS     SYS     SYS     PXB     NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      NODE    NODE    NODE    NODE    NODE                            
NIC11   SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE     X      PIX     NODE    NODE    NODE                            
NIC12   SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    PIX      X      NODE    NODE    NODE                            
NIC13   SYS     SYS     SYS     SYS     NODE    PXB     NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE     X      NODE    NODE                            
NIC14   SYS     SYS     SYS     SYS     NODE    NODE    PXB     NODE    SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE     X      NODE                            
NIC15   SYS     SYS     SYS     SYS     NODE    NODE    NODE    PXB     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    NODE     X                              

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

NIC Legend:

  NIC0: mlx5_0
  NIC1: mlx5_1
  NIC2: mlx5_2
  NIC3: mlx5_3
  NIC4: mlx5_4
  NIC5: mlx5_5
  NIC6: mlx5_6
  NIC7: mlx5_7
  NIC8: mlx5_8
  NIC9: mlx5_9
  NIC10: mlx5_10
  NIC11: mlx5_11
  NIC12: mlx5_12
  NIC13: mlx5_13
  NIC14: mlx5_14
  NIC15: mlx5_15

==============================
     Environment Variables
==============================
LD_LIBRARY_PATH=/home/ProExpertProg/git/vllm/.venv/lib/python3.12/site-packages/cv2/../../lib64:/usr/local/cuda-12.9/lib64:/usr/local/cuda-12.9/lib64
CUDA_HOME=/usr/local/cuda-12.9
CUDA_HOME=/usr/local/cuda-12.9
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_ProExpertProg
VLLM_WORKER_MULTIPROC_METHOD=spawn

</details>

🐛 Describe the bug

$ vllm serve deepseek-ai/DeepSeek-V3 --hf-overrides.num_hidden_layers=4 --load-format=dummy
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292] 
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292]        █     █     █▄   ▄█
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.17.0rc1.dev141+g2347661c4.d20260306
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292]   █▄█▀ █     █     █     █  model   deepseek-ai/DeepSeek-V3
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:292] 
(APIServer pid=2260246) INFO 03-09 13:38:04 [utils.py:228] non-default args: {'model_tag': 'deepseek-ai/DeepSeek-V3', 'model': 'deepseek-ai/DeepSeek-V3', 'hf_overrides': {'num_hidden_layers': 4}, 'load_format': 'dummy'}
(APIServer pid=2260246) INFO 03-09 13:38:04 [model.py:531] Resolved architecture: DeepseekV3ForCausalLM
(APIServer pid=2260246) INFO 03-09 13:38:04 [model.py:1554] Using max model len 163840
(APIServer pid=2260246) INFO 03-09 13:38:04 [scheduler.py:231] Chunked prefill is enabled with max_num_batched_tokens=8192.
(APIServer pid=2260246) INFO 03-09 13:38:04 [vllm.py:754] Asynchronous scheduling is enabled.
(APIServer pid=2260246) INFO 03-09 13:38:04 [compilation.py:286] Enabled custom fusions: norm_quant, act_quant
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:11 [core.py:103] Initializing a V1 LLM engine (v0.17.0rc1.dev141+g2347661c4.d20260306) with config: model='deepseek-ai/DeepSeek-V3', speculative_config=None, tokenizer='deepseek-ai/DeepSeek-V3', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=163840, download_dir=None, load_format=dummy, 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=fp8, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', 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=deepseek-ai/DeepSeek-V3, 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_split_points': [8192], '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_DP0 pid=2260746) INFO 03-09 13:38:12 [parallel_state.py:1395] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://10.14.216.12:59919 backend=nccl
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:12 [parallel_state.py:1717] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank 0, EPLB rank N/A
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [gpu_model_runner.py:4455] Starting to load model deepseek-ai/DeepSeek-V3...
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [cuda.py:317] Using FLASHINFER_MLA attention backend out of potential backends: ['FLASHINFER_MLA', 'CUTLASS_MLA', 'TRITON_MLA'].
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [selector.py:124] Using HND KV cache layout for FLASHINFER_MLA backend.
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [mla_attention.py:2113] Using TRT-LLM ragged DeepSeek prefill for MLA
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [fp8.py:390] Using FLASHINFER_TRTLLM Fp8 MoE backend out of potential backends: ['AITER', 'FLASHINFER_TRTLLM', 'FLASHINFER_CUTLASS', 'DEEPGEMM', 'TRITON', 'MARLIN', 'BATCHED_DEEPGEMM', 'BATCHED_TRITON', 'XPU'].
(EngineCore_DP0 pid=2260746) <frozen importlib._bootstrap_external>:1297: 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.
(EngineCore_DP0 pid=2260746) <frozen importlib._bootstrap_external>:1297: 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.
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [fp8.py:539] Using MoEPrepareAndFinalizeNoDPEPMonolithic
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [gpu_model_runner.py:4538] Model loading took 16.2 GiB memory and 0.499895 seconds
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:13 [interface.py:466] Setting kv cache block size to 32 for FLASHINFER_MLA backend.
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:15 [backends.py:975] Using cache directory: /home/ProExpertProg/.cache/vllm/torch_compile_cache/d6390327fd/rank_0_0/backbone for vLLM's torch.compile
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:15 [backends.py:1035] Dynamo bytecode transform time: 1.54 s
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:16 [backends.py:371] Cache the graph of compile range (1, 8192) for later use
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:17 [backends.py:387] Compiling a graph for compile range (1, 8192) takes 0.80 s
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:17 [decorators.py:606] saved AOT compiled function to /home/ProExpertProg/.cache/vllm/torch_compile_cache/torch_aot_compile/631fac8acbacc2b3373859a29e5c8c10d8dde5d917bea7320b0b0a7f2435d5d4/rank_0_0/model
(EngineCore_DP0 pid=2260746) INFO 03-09 13:38:17 [monitor.py:48] torch.compile took 3.27 s in total

Meanwhile, qwen3 works:

$ vllm serve qwen/qwen3-30b-a3b --hf-overrides.num_hidden_layers=4 --load-format=dummy
...
(APIServer pid=2265759) INFO:     Application startup complete.

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

Fix Plan

To fix the issue of DeepSeek-v3 failing with the error when using --hf-overrides.num_hidden_layers=4, we need to modify the model configuration to accommodate the changed number of hidden layers.

Here are the steps to fix the issue:

Modify the num_hidden_layers parameter in the model configuration to match the desired number of hidden layers.
Update the model architecture to reflect the changed number of hidden layers.

Example code:

import torch

# Define the model configuration
model_config = {
    "num_hidden_layers": 4,
    # Other model configuration parameters...
}

# Create the model with the updated configuration
model = DeepseekV3ForCausalLM(config=model_config)

# Save the updated model
torch.save(model.state_dict(), "updated_model.pth")

In this example, we define a new model configuration with the desired number of hidden layers and create a new instance of the DeepseekV3ForCausalLM model with the updated configuration. We then save the updated model to a file.

Verification

To verify that the fix worked, you can try running the vllm serve command with the updated model:

vllm serve deepseek-ai/DeepSeek-V3 --hf-overrides.num_hidden_layers=4 --load-format=dummy

If the model loads successfully and runs without errors, the fix was successful.

Extra Tips

Make sure to update the model configuration correctly to reflect the changed number of hidden layers.
If you encounter any issues during the update process, refer to the model documentation and the VLLM documentation for troubleshooting guides.
Consider testing the updated model with different inputs and scenarios to ensure it behaves as expected.

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 #ssr #installation #cache error #pipeline error #model loading #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]: DeepSeek hangs with overridden num_hidden_layers [1 comments, 1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

TRENDING

vllm - 💡(How to fix) Fix [Bug]: DeepSeek hangs with overridden num_hidden_layers [1 comments, 1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Before submitting a new issue...

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

RELATED_DISCOVERY

TRENDING