Your current environment

Your output of `python collect_env.py` here

============================== 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-6.8.0-57-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 A100-SXM4-80GB GPU 1: NVIDIA A100-SXM4-80GB

Nvidia driver version : 570.124.06 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: 48 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 256 On-line CPU(s) list: 0-255 Vendor ID: AuthenticAMD Model name: AMD EPYC 7763 64-Core Processor CPU family: 25 Model: 1 Thread(s) per core: 2 Core(s) per socket: 64 Socket(s): 2 Stepping: 1 Frequency boost: enabled CPU max MHz: 3529.0520 CPU min MHz: 1500.0000 BogoMIPS: 4900.46 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin brs arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca debug_swap Virtualization: AMD-V L1d cache: 4 MiB (128 instances) L1i cache: 4 MiB (128 instances) L2 cache: 64 MiB (128 instances) L3 cache: 512 MiB (16 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-63,128-191 NUMA node1 CPU(s): 64-127,192-255 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Mitigation; Safe RET Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

============================== Versions of relevant libraries

[pip3] flashinfer-python==0.6.8.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 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 CPU Affinity NUMA Affinity GPU NUMA ID GPU0 X NV12 SYS SYS SYS SYS NODE NODE PXB PXB 64-127,192-255 1 N/A GPU1 NV12 X SYS SYS SYS SYS NODE NODE PXB PXB 64-127,192-255 1 N/A NIC0 SYS SYS X PXB NODE NODE SYS SYS SYS SYS NIC1 SYS SYS PXB X NODE NODE SYS SYS SYS SYS NIC2 SYS SYS NODE NODE X PXB SYS SYS SYS SYS NIC3 SYS SYS NODE NODE PXB X SYS SYS SYS SYS NIC4 NODE NODE SYS SYS SYS SYS X PXB NODE NODE NIC5 NODE NODE SYS SYS SYS SYS PXB X NODE NODE NIC6 PXB PXB SYS SYS SYS SYS NODE NODE X PXB NIC7 PXB PXB SYS SYS SYS SYS NODE NODE PXB 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

============================== Environment Variables

NVIDIA_VISIBLE_DEVICES=all 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_CONFIG_PATH=/app/logging_config.json PYTORCH_NVML_BASED_CUDA_CHECK=1 TORCHINDUCTOR_COMPILE_THREADS=1 TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

🐛 Describe the bug

During normal LLM inference, vllm occasionally experiences crash with kv offloading_connector. Deployment:

vllm serve google/gemma-4-31B-it \
  --gpu-memory-utilization 0.7 \
  --speculative-config '{"model": "google/gemma-4-31B-it-assistant","num_speculative_tokens": 4,"method": "mtp"}' \
  --max-num-batched-tokens 4096 \
  --enable-auto-tool-choice \
  --tool-call-parser gemma4 \
  --reasoning-parser gemma4 \
  --tensor-parallel-size 2 \
  --default-chat-template-kwargs '{"enable_thinking": false}' \
  --performance-mode interactivity \
  --kv-offloading-size 200 \
  --kv-offloading-backend native \
  --enable-prefix-caching \
  --enable-prompt-tokens-details \
  --enable-force-include-usage

No particular usage pattern is observed that will definitely trigger. Just happens randomly sometimes.

(APIServer pid=1) INFO 05-27 18:56:19 metrics.py:103] KV Transfer metrics: GPU_to_CPU_total_bytes=201850880, GPU_to_CPU_total_time=0.08097408032417297, CPU_to_GPU_total_bytes=57671680, CPU_to_GPU_total_time=0.006535071849822998 (APIServer pid=1) INFO 05-27 18:56:29 loggers.py:271] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 21.7%, External prefix cache hit rate: 3.5%, MM cache hit rate: 63.6% (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] EngineCore encountered a fatal error. (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] Traceback (most recent call last): (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 1133, in run_engine_core (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] engine_core.run_busy_loop() (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 1174, in run_busy_loop (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] self._process_engine_step() (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 1213, in _process_engine_step (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] outputs, model_executed = self.step_fn() (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] ^^^^^^^^^^^^^^ (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 475, in step_with_batch_queue (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] scheduler_output = self.scheduler.schedule() (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] ^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/core/sched/scheduler.py", line 728, in schedule (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] self.connector.update_state_after_alloc( (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 132, in update_state_after_alloc (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] return self.connector_scheduler.update_state_after_alloc( (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading/scheduler.py", line 529, in update_state_after_alloc (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] num_locally_computed_tokens (EngineCore pid=463) ERROR 05-27 18:56:31 core.py:1142] AssertionError (Worker_TP0 pid=662) INFO 05-27 18:56:31 multiproc_executor.py:775] Parent process exited, terminating worker queues (APIServer pid=1) ERROR 05-27 18:56:31 async_llm.py:704] AsyncLLM output_handler failed. (APIServer pid=1) ERROR 05-27 18:56:31 async_llm.py:704] Traceback (most recent call last): (APIServer pid=1) ERROR 05-27 18:56:31 async_llm.py:704] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 660, in output_handler (APIServer pid=1) ERROR 05-27 18:56:31 async_llm.py:704] outputs = await engine_core.get_output_async() (APIServer pid=1) ERROR 05-27 18:56:31 async_llm.py:704] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) ERROR 05-27 18:56:31 async_llm.py:704] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py", line 998, in get_output_async (APIServer pid=1) ERROR 05-27 18:56:31 async_llm.py:704] raise self._format_exception(outputs) from None (APIServer pid=1) ERROR 05-27 18:56:31 async_llm.py:704] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause. (Worker_TP0 pid=662) INFO 05-27 18:56:31 multiproc_executor.py:872] WorkerProc shutting down. (Worker_TP1 pid=663) INFO 05-27 18:56:31 multiproc_executor.py:872] WorkerProc shutting down. (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] Error in chat completion stream generator. (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] Traceback (most recent call last): (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/chat_completion/serving.py", line 496, in chat_completion_stream_generator (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] async for res in result_generator: (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 579, in generate (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] out = q.get_nowait() or await q.get() (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] ^^^^^^^^^^^^^ (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/output_processor.py", line 88, in get (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] raise output (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 660, in output_handler (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] outputs = await engine_core.get_output_async() (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py", line 998, in get_output_async (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] raise self._format_exception(outputs) from None (APIServer pid=1) ERROR 05-27 18:56:31 serving.py:997] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause.

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.