Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Bug]: vllm:cache_config_info reports stale block_size=16 for hybrid Mamba models

Official PRs (…)
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.

Helpful · Quick feedback

Loading…

When serving hybrid Mamba models (e.g. Qwen/Qwen3.6-35B-A3B, architecture Qwen3_5MoeForConditionalGeneration), _align_hybrid_block_size() correctly enlarges block_size in the worker process (e.g. to 528 or 1056 tokens) to ensure the attention page size is >= the Mamba page size. However, this updated value is never synced back to the parent APIServer process, so the Prometheus metric vllm:cache_config_info reports the stale default block_size=16.

Root Cause

EngineCoreReadyResponse (vllm/v1/engine/init.py) is used to sync post-initialization state from the EngineCore subprocess back to the frontend. It syncs max_model_len and num_gpu_blocks, but not block_size. The update to cache_config.block_size made by _align_hybrid_block_size() in the worker (vllm/platforms/interface.py) therefore never reaches the APIServer process where Prometheus metrics are emitted.

Fix Action

Fix

Add block_size: int to EngineCoreReadyResponse, populate it in core.py when constructing the response, and sync it back in core_client.py's _apply_ready_response() using max() (safe for the DP multi-engine case since workers only ever increase block_size).

Code Example

Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.11.0+cu129
Is debug build               : False
CUDA used to build PyTorch   : 12.9
ROCM used to build PyTorch   : N/A
XPU used to build PyTorch    : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Mar  4 2026, 09:23:07) [GCC 11.4.0] (64-bit runtime)
Python platform              : Linux-5.15.0-176-generic-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.9.86
CUDA_MODULE_LOADING set to   :
GPU models and configuration :
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3

Nvidia driver version        : 580.65.06
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:                           46 bits physical, 57 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  176
On-line CPU(s) list:                     0-175
Vendor ID:                               GenuineIntel
Model name:                              Intel(R) Xeon(R) Platinum 8468V
CPU family:                              6
Model:                                   143
Thread(s) per core:                      2
Core(s) per socket:                      44
Socket(s):                               2
Stepping:                                8
BogoMIPS:                                4800.00
Flags:                                   fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk avx512_fp16 arch_capabilities
Virtualization:                          VT-x
Hypervisor vendor:                       KVM
Virtualization type:                     full
L1d cache:                               4.1 MiB (88 instances)
L1i cache:                               2.8 MiB (88 instances)
L2 cache:                                176 MiB (88 instances)
L3 cache:                                195 MiB (2 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-87
NUMA node1 CPU(s):                       88-175
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Mitigation; Aligned branch/return thunks
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 and seccomp
Vulnerability Spectre v1:                Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Mitigation; TSX disabled
Vulnerability Vmscape:                   Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.8.post1
[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==9.17.1.4
[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==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu12==2.28.9
[pip3] nvidia-nvjitlink-cu12==12.9.86
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] pyzmq==27.1.0
[pip3] tokenspeed-triton==3.7.10.post20260505
[pip3] torch==2.11.0+cu129
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.11.0+cu129
[pip3] torchvision==0.26.0+cu129
[pip3] transformers==5.8.1
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.21.0
vLLM Build Flags:
  CUDA Archs: 7.5 8.0 8.6 8.9 9.0 10.0 12.0; ROCm: Disabled; XPU: Disabled
GPU Topology:
  	GPU0	GPU1	GPU2	GPU3	NIC0	NIC1	NIC2	NIC3	NIC4	NIC5	NIC6	NIC7	NIC8	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	NV18	NV18	NV18	NODE	PHB	PHB	PHB	PHB	SYS	SYS	SYS	SYS	0-87	0		N/A
GPU1	NV18	 X 	NV18	NV18	NODE	PHB	PHB	PHB	PHB	SYS	SYS	SYS	SYS	0-87	0		N/A
GPU2	NV18	NV18	 X 	NV18	NODE	PHB	PHB	PHB	PHB	SYS	SYS	SYS	SYS	0-87	0		N/A
GPU3	NV18	NV18	NV18	 X 	NODE	PHB	PHB	PHB	PHB	SYS	SYS	SYS	SYS	0-87	0		N/A
NIC0	NODE	NODE	NODE	NODE	 X 	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS				
NIC1	PHB	PHB	PHB	PHB	NODE	 X 	PHB	PHB	PHB	SYS	SYS	SYS	SYS				
NIC2	PHB	PHB	PHB	PHB	NODE	PHB	 X 	PHB	PHB	SYS	SYS	SYS	SYS				
NIC3	PHB	PHB	PHB	PHB	NODE	PHB	PHB	 X 	PHB	SYS	SYS	SYS	SYS				
NIC4	PHB	PHB	PHB	PHB	NODE	PHB	PHB	PHB	 X 	SYS	SYS	SYS	SYS				
NIC5	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	PHB	PHB	PHB				
NIC6	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PHB	 X 	PHB	PHB				
NIC7	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PHB	PHB	 X 	PHB				
NIC8	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PHB	PHB	PHB	 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

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=GPU-e1d001ad-cca9-9905-f575-4027b1f11a51,GPU-88d7cd04-4b46-c164-ce90-ab7187b24b48,GPU-307c6e31-7e9a-cf36-2be3-744bc954f926,GPU-cd205fa2-1e1a-191e-ee0c-b830fb71de4b
NVIDIA_REQUIRE_CUDA=cuda>=12.9 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571
TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.9 9.0 10.0 12.0
NVIDIA_DRIVER_CAPABILITIES=compute,utility
VLLM_USAGE_SOURCE=production-docker-image
CUDA_VERSION=12.9.1
VLLM_ENABLE_CUDA_COMPATIBILITY=0
LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64
VLLM_LOGGING_LEVEL=INFO
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root
RAW_BUFFERClick to expand / collapse

Your current environment

<details> <summary>The output of <code>python collect_env.py</code></summary> 
Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.11.0+cu129
Is debug build               : False
CUDA used to build PyTorch   : 12.9
ROCM used to build PyTorch   : N/A
XPU used to build PyTorch    : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Mar  4 2026, 09:23:07) [GCC 11.4.0] (64-bit runtime)
Python platform              : Linux-5.15.0-176-generic-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.9.86
CUDA_MODULE_LOADING set to   :
GPU models and configuration :
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3

Nvidia driver version        : 580.65.06
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:                           46 bits physical, 57 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  176
On-line CPU(s) list:                     0-175
Vendor ID:                               GenuineIntel
Model name:                              Intel(R) Xeon(R) Platinum 8468V
CPU family:                              6
Model:                                   143
Thread(s) per core:                      2
Core(s) per socket:                      44
Socket(s):                               2
Stepping:                                8
BogoMIPS:                                4800.00
Flags:                                   fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk avx512_fp16 arch_capabilities
Virtualization:                          VT-x
Hypervisor vendor:                       KVM
Virtualization type:                     full
L1d cache:                               4.1 MiB (88 instances)
L1i cache:                               2.8 MiB (88 instances)
L2 cache:                                176 MiB (88 instances)
L3 cache:                                195 MiB (2 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-87
NUMA node1 CPU(s):                       88-175
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Mitigation; Aligned branch/return thunks
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 and seccomp
Vulnerability Spectre v1:                Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Mitigation; TSX disabled
Vulnerability Vmscape:                   Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.8.post1
[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==9.17.1.4
[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==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu12==2.28.9
[pip3] nvidia-nvjitlink-cu12==12.9.86
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] pyzmq==27.1.0
[pip3] tokenspeed-triton==3.7.10.post20260505
[pip3] torch==2.11.0+cu129
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.11.0+cu129
[pip3] torchvision==0.26.0+cu129
[pip3] transformers==5.8.1
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.21.0
vLLM Build Flags:
  CUDA Archs: 7.5 8.0 8.6 8.9 9.0 10.0 12.0; ROCm: Disabled; XPU: Disabled
GPU Topology:
  	GPU0	GPU1	GPU2	GPU3	NIC0	NIC1	NIC2	NIC3	NIC4	NIC5	NIC6	NIC7	NIC8	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	NV18	NV18	NV18	NODE	PHB	PHB	PHB	PHB	SYS	SYS	SYS	SYS	0-87	0		N/A
GPU1	NV18	 X 	NV18	NV18	NODE	PHB	PHB	PHB	PHB	SYS	SYS	SYS	SYS	0-87	0		N/A
GPU2	NV18	NV18	 X 	NV18	NODE	PHB	PHB	PHB	PHB	SYS	SYS	SYS	SYS	0-87	0		N/A
GPU3	NV18	NV18	NV18	 X 	NODE	PHB	PHB	PHB	PHB	SYS	SYS	SYS	SYS	0-87	0		N/A
NIC0	NODE	NODE	NODE	NODE	 X 	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS				
NIC1	PHB	PHB	PHB	PHB	NODE	 X 	PHB	PHB	PHB	SYS	SYS	SYS	SYS				
NIC2	PHB	PHB	PHB	PHB	NODE	PHB	 X 	PHB	PHB	SYS	SYS	SYS	SYS				
NIC3	PHB	PHB	PHB	PHB	NODE	PHB	PHB	 X 	PHB	SYS	SYS	SYS	SYS				
NIC4	PHB	PHB	PHB	PHB	NODE	PHB	PHB	PHB	 X 	SYS	SYS	SYS	SYS				
NIC5	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	PHB	PHB	PHB				
NIC6	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PHB	 X 	PHB	PHB				
NIC7	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PHB	PHB	 X 	PHB				
NIC8	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PHB	PHB	PHB	 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

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=GPU-e1d001ad-cca9-9905-f575-4027b1f11a51,GPU-88d7cd04-4b46-c164-ce90-ab7187b24b48,GPU-307c6e31-7e9a-cf36-2be3-744bc954f926,GPU-cd205fa2-1e1a-191e-ee0c-b830fb71de4b
NVIDIA_REQUIRE_CUDA=cuda>=12.9 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571
TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.9 9.0 10.0 12.0
NVIDIA_DRIVER_CAPABILITIES=compute,utility
VLLM_USAGE_SOURCE=production-docker-image
CUDA_VERSION=12.9.1
VLLM_ENABLE_CUDA_COMPATIBILITY=0
LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64
VLLM_LOGGING_LEVEL=INFO
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root
</details>

🐛 Describe the bug

Description

When serving hybrid Mamba models (e.g. Qwen/Qwen3.6-35B-A3B, architecture Qwen3_5MoeForConditionalGeneration), _align_hybrid_block_size() correctly enlarges block_size in the worker process (e.g. to 528 or 1056 tokens) to ensure the attention page size is >= the Mamba page size. However, this updated value is never synced back to the parent APIServer process, so the Prometheus metric vllm:cache_config_info reports the stale default block_size=16.

Reproduction

Running an Hybrid model, for example:

vllm serve Qwen/Qwen3.6-35B-A3B --tensor-parallel-size 4

Startup log shows:

[interface.py:645] Setting attention block size to 528 tokens to ensure that attention page size is >= mamba page size.

But when I do curl http://localhost:8000/metrics I see:

vllm:cache_config_info{block_size="16", ...}

Root cause

EngineCoreReadyResponse (vllm/v1/engine/init.py) is used to sync post-initialization state from the EngineCore subprocess back to the frontend. It syncs max_model_len and num_gpu_blocks, but not block_size. The update to cache_config.block_size made by _align_hybrid_block_size() in the worker (vllm/platforms/interface.py) therefore never reaches the APIServer process where Prometheus metrics are emitted.

Fix

Add block_size: int to EngineCoreReadyResponse, populate it in core.py when constructing the response, and sync it back in core_client.py's _apply_ready_response() using max() (safe for the DP multi-engine case since workers only ever increase block_size).

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.

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?
Loading…
#api#environment variable#cache issue#memory leak#API versioning

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

vllm - 💡(How to fix) Fix [Bug]: vllm:cache_config_info reports stale block_size=16 for hybrid Mamba models