vllm - ✅(Solved) Fix [Bug]: V1 + Ray multi-node pipeline parallel `KeyError` at KV-cache init due to missing `global_rank` update [1 pull requests, 1 participants]

vllm2026-04-29 20:58:22

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#41287•Fetched 2026-04-30 06:19:02

View on GitHub

Comments

Participants

Timeline

Reactions

Author

jamesbraza

Participants

jamesbraza

Timeline (top)

cross-referenced ×1labeled ×1

Error Message

ray.exceptions.RayTaskError(KeyError): ray::RayWorkerWrapper.execute_method() (...) File ".../vllm/v1/worker/gpu_worker.py", line 536, in initialize_from_config self.model_runner.initialize_kv_cache(kv_cache_config) File ".../vllm/v1/worker/gpu_model_runner.py", line 6781, in initialize_kv_cache self.initialize_attn_backend(kv_cache_config) File ".../vllm/v1/worker/gpu_model_runner.py", line 6204, in initialize_attn_backend attn_backends = get_attn_backends_for_group(kv_cache_group_spec) File ".../vllm/v1/worker/gpu_model_runner.py", line 6163, in get_attn_backends_for_group attn_backend = layers[layer_name].get_attn_backend() ~~~~~~^^^^^^^^^^^^ KeyError: 'model.layers.21.self_attn.attn'

Root Cause

This bug was introduced in https://github.com/vllm-project/vllm/pull/23691, which broke the Ray path on pipeline parallel above 1, because adjust_rank doesn't reset global_rank.

Fix Action

Fix / Workaround

============================== 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): 104 On-line CPU(s) list: 0-103 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Platinum 8470 CPU family: 6 Model: 143 Thread(s) per core: 1 Core(s) per socket: 52 Socket(s): 2 Stepping: 8 CPU max MHz: 3800.0000 CPU min MHz: 800.0000 BogoMIPS: 4000.00 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 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 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced 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 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 ibpb_exit_to_user L1d cache: 4.9 MiB (104 instances) L1i cache: 3.3 MiB (104 instances) L2 cache: 208 MiB (104 instances) L3 cache: 210 MiB (2 instances) NUMA node(s): 8 NUMA node0 CPU(s): 0-12 NUMA node1 CPU(s): 13-25 NUMA node2 CPU(s): 26-38 NUMA node3 CPU(s): 39-51 NUMA node4 CPU(s): 52-64 NUMA node5 CPU(s): 65-77 NUMA node6 CPU(s): 78-90 NUMA node7 CPU(s): 91-103 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 Vulnerability Vmscape: Mitigation; IBPB before exit to userspace

PR fix notes

PR #41298: [Bugfix] V1 Ray: sync `global_rank` in `adjust_rank` for PP > 1

Repository: vllm-project/vllm
Author: jamesbraza
State: open | merged: False
Link: https://github.com/vllm-project/vllm/pull/41298

Description (problem / solution / changelog)

Purpose

Fixes https://github.com/vllm-project/vllm/issues/41287.

This bugfix PR keeps rpc_rank and global_rank in-sync in RayWorkerWrapper.

Test Plan

Newly-added test test_adjust_rank_keeps_global_rank_in_sync passes:

pytest tests/v1/executor/test_ray_utils.py

Test Result

Passing tests

Changed files

tests/v1/executor/test_ray_utils.py (modified, +22/-1)
vllm/v1/executor/ray_utils.py (modified, +3/-0)

Code Example

==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.35

==============================
       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
XPU used to build PyTorch    : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Apr  7 2026, 20:45:25) [Clang 22.1.1 ] (64-bit runtime)
Python platform              : Linux-6.8.0-1043-nvidia-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
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3

Nvidia driver version        : 575.57.08
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):                               104
On-line CPU(s) list:                  0-103
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Platinum 8470
CPU family:                           6
Model:                                143
Thread(s) per core:                   1
Core(s) per socket:                   52
Socket(s):                            2
Stepping:                             8
CPU max MHz:                          3800.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4000.00
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 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 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced 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 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 ibpb_exit_to_user
L1d cache:                            4.9 MiB (104 instances)
L1i cache:                            3.3 MiB (104 instances)
L2 cache:                             208 MiB (104 instances)
L3 cache:                             210 MiB (2 instances)
NUMA node(s):                         8
NUMA node0 CPU(s):                    0-12
NUMA node1 CPU(s):                    13-25
NUMA node2 CPU(s):                    26-38
NUMA node3 CPU(s):                    39-51
NUMA node4 CPU(s):                    52-64
NUMA node5 CPU(s):                    65-77
NUMA node6 CPU(s):                    78-90
NUMA node7 CPU(s):                    91-103
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
Vulnerability Vmscape:                Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.6
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.9.1.4
[pip3] nvidia-cuda-cupti-cu12==12.9.79
[pip3] nvidia-cuda-nvcc-cu12==12.9.86
[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==4.4.2
[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==12.9.86
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] pyzmq==27.1.0
[pip3] sentence-transformers==5.4.1
[pip3] torch==2.10.0+cu129
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0
[pip3] torchdata==0.11.0
[pip3] torchvision==0.25.0
[pip3] transformers==5.5.4
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.19.1
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled; XPU: Disabled
GPU Topology:
  	GPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	NIC0	NIC1	NIC2	NIC3	NIC4	NIC5	NIC6	NIC7	NIC8	NIC9	NIC10	NIC11	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NV18	PIX	PIX	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	0-12	0		N/A
GPU1	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NV18	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	26-38	2		N/A
GPU2	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NV18	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	39-51	3		N/A
GPU3	NV18	NV18	NV18	 X 	NV18	NV18	NV18	NV18	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	13-25	1		N/A
GPU4	NV18	NV18	NV18	NV18	 X 	NV18	NV18	NV18	SYS	SYS	SYS	SYS	SYS	SYS	PIX	PIX	PIX	SYS	SYS	SYS	52-64	4		N/A
GPU5	NV18	NV18	NV18	NV18	NV18	 X 	NV18	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	78-90	6		N/A
GPU6	NV18	NV18	NV18	NV18	NV18	NV18	 X 	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	SYS	91-103	7		N/A
GPU7	NV18	NV18	NV18	NV18	NV18	NV18	NV18	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	65-77	5		N/A
NIC0	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	PIX	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC1	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	 X 	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC2	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	PIX	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC3	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC4	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC5	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS	SYS	SYS	SYS	SYS	SYS
NIC6	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	PIX	PIX	SYS	SYS	SYS
NIC7	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	 X 	PIX	SYS	SYS	SYS
NIC8	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	PIX	 X 	SYS	SYS	SYS
NIC9	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS	SYS
NIC10	SYS	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS
NIC11	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 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

==============================
     Environment Variables
==============================
LD_LIBRARY_PATH=/lib/x86_64-linux-gnu:/usr/lib/x86_64-linux-gnu:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/targets/x86_64-linux/lib:/opt/hpcx/ompi/lib:/opt/hpcx/hcoll/lib:/opt/hpcx/sharp/lib:/opt/hpcx/ucx/lib:/opt/hpcx/ucx/lib/ucx:/opt/hpcx/ucc/lib:/opt/hpcx/ucc/lib/ucc:/opt/hpcx/nccl_rdma_sharp_plugin/lib:/usr/local/cuda/lib64:
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_james

---

ray.exceptions.RayTaskError(KeyError): ray::RayWorkerWrapper.execute_method() (...)
  File ".../vllm/v1/worker/gpu_worker.py", line 536, in initialize_from_config
    self.model_runner.initialize_kv_cache(kv_cache_config)
  File ".../vllm/v1/worker/gpu_model_runner.py", line 6781, in initialize_kv_cache
    self.initialize_attn_backend(kv_cache_config)
  File ".../vllm/v1/worker/gpu_model_runner.py", line 6204, in initialize_attn_backend
    attn_backends = get_attn_backends_for_group(kv_cache_group_spec)
  File ".../vllm/v1/worker/gpu_model_runner.py", line 6163, in get_attn_backends_for_group
    attn_backend = layers[layer_name].get_attn_backend()
                   ~~~~~~^^^^^^^^^^^^
KeyError: 'model.layers.21.self_attn.attn'

---

# Bring up Ray across the allocation, then:
vllm serve "Qwen/Qwen3-32B" \
  --tensor-parallel-size 8 --pipeline-parallel-size 3 \
  --distributed-executor-backend ray

RAW_BUFFERClick to expand / collapse

Your current environment

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

==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.35

==============================
       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
XPU used to build PyTorch    : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Apr  7 2026, 20:45:25) [Clang 22.1.1 ] (64-bit runtime)
Python platform              : Linux-6.8.0-1043-nvidia-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
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3

Nvidia driver version        : 575.57.08
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):                               104
On-line CPU(s) list:                  0-103
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Platinum 8470
CPU family:                           6
Model:                                143
Thread(s) per core:                   1
Core(s) per socket:                   52
Socket(s):                            2
Stepping:                             8
CPU max MHz:                          3800.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4000.00
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 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 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced 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 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 ibpb_exit_to_user
L1d cache:                            4.9 MiB (104 instances)
L1i cache:                            3.3 MiB (104 instances)
L2 cache:                             208 MiB (104 instances)
L3 cache:                             210 MiB (2 instances)
NUMA node(s):                         8
NUMA node0 CPU(s):                    0-12
NUMA node1 CPU(s):                    13-25
NUMA node2 CPU(s):                    26-38
NUMA node3 CPU(s):                    39-51
NUMA node4 CPU(s):                    52-64
NUMA node5 CPU(s):                    65-77
NUMA node6 CPU(s):                    78-90
NUMA node7 CPU(s):                    91-103
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
Vulnerability Vmscape:                Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.6
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.9.1.4
[pip3] nvidia-cuda-cupti-cu12==12.9.79
[pip3] nvidia-cuda-nvcc-cu12==12.9.86
[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==4.4.2
[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==12.9.86
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] pyzmq==27.1.0
[pip3] sentence-transformers==5.4.1
[pip3] torch==2.10.0+cu129
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0
[pip3] torchdata==0.11.0
[pip3] torchvision==0.25.0
[pip3] transformers==5.5.4
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.19.1
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled; XPU: Disabled
GPU Topology:
  	GPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	NIC0	NIC1	NIC2	NIC3	NIC4	NIC5	NIC6	NIC7	NIC8	NIC9	NIC10	NIC11	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NV18	PIX	PIX	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	0-12	0		N/A
GPU1	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NV18	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	26-38	2		N/A
GPU2	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NV18	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	39-51	3		N/A
GPU3	NV18	NV18	NV18	 X 	NV18	NV18	NV18	NV18	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	13-25	1		N/A
GPU4	NV18	NV18	NV18	NV18	 X 	NV18	NV18	NV18	SYS	SYS	SYS	SYS	SYS	SYS	PIX	PIX	PIX	SYS	SYS	SYS	52-64	4		N/A
GPU5	NV18	NV18	NV18	NV18	NV18	 X 	NV18	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	78-90	6		N/A
GPU6	NV18	NV18	NV18	NV18	NV18	NV18	 X 	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	SYS	91-103	7		N/A
GPU7	NV18	NV18	NV18	NV18	NV18	NV18	NV18	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	65-77	5		N/A
NIC0	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	PIX	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC1	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	 X 	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC2	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	PIX	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC3	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC4	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS
NIC5	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS	SYS	SYS	SYS	SYS	SYS
NIC6	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	PIX	PIX	SYS	SYS	SYS
NIC7	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	 X 	PIX	SYS	SYS	SYS
NIC8	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	PIX	 X 	SYS	SYS	SYS
NIC9	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS	SYS
NIC10	SYS	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	SYS
NIC11	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PIX	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 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

==============================
     Environment Variables
==============================
LD_LIBRARY_PATH=/lib/x86_64-linux-gnu:/usr/lib/x86_64-linux-gnu:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/targets/x86_64-linux/lib:/opt/hpcx/ompi/lib:/opt/hpcx/hcoll/lib:/opt/hpcx/sharp/lib:/opt/hpcx/ucx/lib:/opt/hpcx/ucx/lib/ucx:/opt/hpcx/ucc/lib:/opt/hpcx/ucc/lib/ucc:/opt/hpcx/nccl_rdma_sharp_plugin/lib:/usr/local/cuda/lib64:
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_james

</details>

🐛 Describe the bug

vllm serve with multi-node pipeline parallelism on V1 + Ray fails deterministically during KV-cache initialization with KeyError 'model.layers.<N>.self_attn.attn', where N is the first layer of some other pipeline parallel shard:

ray.exceptions.RayTaskError(KeyError): ray::RayWorkerWrapper.execute_method() (...)
  File ".../vllm/v1/worker/gpu_worker.py", line 536, in initialize_from_config
    self.model_runner.initialize_kv_cache(kv_cache_config)
  File ".../vllm/v1/worker/gpu_model_runner.py", line 6781, in initialize_kv_cache
    self.initialize_attn_backend(kv_cache_config)
  File ".../vllm/v1/worker/gpu_model_runner.py", line 6204, in initialize_attn_backend
    attn_backends = get_attn_backends_for_group(kv_cache_group_spec)
  File ".../vllm/v1/worker/gpu_model_runner.py", line 6163, in get_attn_backends_for_group
    attn_backend = layers[layer_name].get_attn_backend()
                   ~~~~~~^^^^^^^^^^^^
KeyError: 'model.layers.21.self_attn.attn'

Each pipeline parallel rank ends up using another shard's projected KV-cache config, so when gpu_model_runner.initialize_attn_backend iterates kv_cache_group_spec.layer_names against the worker-local layers dict, the first layer that doesn't belong to this worker raises the above KeyError.

To reproduce, I used 3 nodes × 8 H100, Qwen3-32B, TP=8 PP=3:

# Bring up Ray across the allocation, then:
vllm serve "Qwen/Qwen3-32B" \
  --tensor-parallel-size 8 --pipeline-parallel-size 3 \
  --distributed-executor-backend ray

Across pipeline parallel ranks in a single run:

failing worker IP	KeyError layer	shard the layer belongs to
192.168.28.43 (head)	`layers.21`	PP rank 1's first layer
192.168.29.211	`layers.0`	PP rank 0's first layer
192.168.28.43 (head)	`layers.43`	PP rank 2's first layer

Every failure is on the first layer of some shard the worker doesn't own... the worker is iterating a layer-name list it should never have received.

This bug was introduced in https://github.com/vllm-project/vllm/pull/23691, which broke the Ray path on pipeline parallel above 1, because adjust_rank doesn't reset global_rank.

The suggested fix is adding self.global_rank = self.rpc_rank into adjust_rank's conditional. That:

Restores the global_rank == rpc_rank invariant that WorkerWrapperBase.__init__ sets when no override is passed.
Re-aligns the per-worker kv_cache_configs indexing with the order the engine core built that list.

extent analysis

TL;DR

The bug can be fixed by adding self.global_rank = self.rpc_rank to the adjust_rank function to restore the global_rank == rpc_rank invariant.

Guidance

The issue arises from the adjust_rank function not resetting global_rank when using Ray with pipeline parallelism above 1.
The suggested fix involves modifying the adjust_rank function to set self.global_rank = self.rpc_rank when the conditional is met.
This change will ensure that the per-worker kv_cache_configs indexing aligns with the order the engine core built that list.
To verify the fix, run the vllm serve command with the modified code and check for the absence of the KeyError exception.

Example

No code example is provided as the fix involves a specific modification to the existing codebase.

Notes

The fix is specific to the Ray path with pipeline parallelism above 1 and may not affect other execution paths.

Recommendation

Apply the suggested fix by adding self.global_rank = self.rpc_rank to the adjust_rank function, as this will restore the necessary invariant and align the kv_cache_configs indexing.

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 #configuration error #environment variable #network issue #logging issue

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 - ✅(Solved) Fix [Bug]: V1 + Ray multi-node pipeline parallel `KeyError` at KV-cache init due to missing `global_rank` update [1 pull requests, 1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Fix / Workaround

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

PR fix notes

PR #41298: [Bugfix] V1 Ray: sync `global_rank` in `adjust_rank` for PP > 1

Description (problem / solution / changelog)

Purpose

Test Plan

Test Result

Changed files

Code Example

Your current environment

🐛 Describe the bug

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

vllm - ✅(Solved) Fix [Bug]: V1 + Ray multi-node pipeline parallel `KeyError` at KV-cache init due to missing `global_rank` update [1 pull requests, 1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Fix / Workaround

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

PR fix notes

PR #41298: [Bugfix] V1 Ray: sync global_rank in adjust_rank for PP > 1

Description (problem / solution / changelog)

Purpose

Test Plan

Test Result

Changed files

Code Example

Your current environment

🐛 Describe the bug

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING

PR #41298: [Bugfix] V1 Ray: sync `global_rank` in `adjust_rank` for PP > 1