[Bug]: illegal memory access error when using prefix caching

[StevenTang1998]

Your current environment

The output of `python collect_env.py`

PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.3 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.27.9
Libc version: glibc-2.35

Python version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.10.134-16.101.al8.x86_64-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA L20Y
GPU 1: NVIDIA L20Y
GPU 2: NVIDIA L20Y
GPU 3: NVIDIA L20Y

Nvidia driver version: 535.161.08
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.7
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.7
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
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):                          192
On-line CPU(s) list:             0-191
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:              48
Socket(s):                       2
Stepping:                        8
CPU max MHz:                     3800.0000
CPU min MHz:                     800.0000
BogoMIPS:                        4800.00
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 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req hfi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm uintr md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                  VT-x
L1d cache:                       4.5 MiB (96 instances)
L1i cache:                       3 MiB (96 instances)
L2 cache:                        192 MiB (96 instances)
L3 cache:                        195 MiB (2 instances)
NUMA node(s):                    2
NUMA node0 CPU(s):               0-47,96-143
NUMA node1 CPU(s):               48-95,144-191
Vulnerability Itlb multihit:     Not affected
Vulnerability L1tf:              Not affected
Vulnerability Mds:               Not affected
Vulnerability Meltdown:          Not affected
Vulnerability Mmio stale data:   Not affected
Vulnerability Retbleed:          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 IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Not affected

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-dali-cuda120==1.32.0
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] nvidia-pyindex==1.0.9
[pip3] onnx==1.15.0rc2
[pip3] optree==0.10.0
[pip3] pynvml==11.5.3
[pip3] pytorch-quantization==2.1.2
[pip3] pyzmq==25.1.2
[pip3] torch==2.4.0
[pip3] torch-tensorrt==2.2.0a0
[pip3] torchdata==0.7.0a0
[pip3] torchtext==0.17.0a0
[pip3] torchvision==0.19.0
[pip3] transformers==4.46.0
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.0.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.3.post1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    GPU1    GPU2    GPU3    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    NIC6    NIC7    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV8     NV8     NV8     SYS     SYS     SYS     SYS     PIX     NODE    NODE    NODE    48-95,144-191   1               N/A
GPU1    NV8      X      NV8     NV8     SYS     SYS     SYS     SYS     NODE    PIX     NODE    NODE    48-95,144-191   1               N/A
GPU2    NV8     NV8      X      NV8     SYS     SYS     SYS     SYS     NODE    NODE    PIX     NODE    48-95,144-191   1               N/A
GPU3    NV8     NV8     NV8      X      SYS     SYS     SYS     SYS     NODE    NODE    NODE    PIX     48-95,144-191   1               N/A
NIC0    SYS     SYS     SYS     SYS      X      NODE    NODE    NODE    SYS     SYS     SYS     SYS
NIC1    SYS     SYS     SYS     SYS     NODE     X      NODE    NODE    SYS     SYS     SYS     SYS
NIC2    SYS     SYS     SYS     SYS     NODE    NODE     X      NODE    SYS     SYS     SYS     SYS
NIC3    SYS     SYS     SYS     SYS     NODE    NODE    NODE     X      SYS     SYS     SYS     SYS
NIC4    PIX     NODE    NODE    NODE    SYS     SYS     SYS     SYS      X      NODE    NODE    NODE
NIC5    NODE    PIX     NODE    NODE    SYS     SYS     SYS     SYS     NODE     X      NODE    NODE
NIC6    NODE    NODE    PIX     NODE    SYS     SYS     SYS     SYS     NODE    NODE     X      NODE
NIC7    NODE    NODE    NODE    PIX     SYS     SYS     SYS     SYS     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_bond_0
  NIC1: mlx5_bond_1
  NIC2: mlx5_bond_2
  NIC3: mlx5_bond_3
  NIC4: mlx5_bond_4
  NIC5: mlx5_bond_5
  NIC6: mlx5_bond_6
  NIC7: mlx5_bond_7

Model Input Dumps

No response

🐛 Describe the bug

As discussed in #9532, setting enable_prefix_caching=True leads to illegal memory access error when using 8 H100 GPUs.

This is the code to reproduce the error:

import torch

from vllm import LLM, SamplingParams


sampling_params = SamplingParams(temperature=0, max_tokens=8192, seed=1234)
llm = LLM(model='Qwen/Qwen2.5-72B-Instruct', enable_prefix_caching=True, tensor_parallel_size=8, enable_chunked_prefill=False)

prompts = torch.load('test.id')
outputs = llm.generate(prompts, sampling_params=sampling_params, use_tqdm=False)

test.id.zip

Please unzip the file to get test.id

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.

[wallashss]

Hey, I am interested in this problem as well with H100.

One question: Have you tried to disable CUDA Graphs with enforce_eager=True? Does it change at least your error?

[StevenTang1998]

Yes, it works.

[wallashss]

Tks @StevenTang1998

[luffydream]

--enforce-eager will disable cudagraph. So , How can i enable multi-steps and cudagraph at the same time?

[luffydream]

--enforce-eager will disable cudagraph. So , How can i enable multi-steps and cudagraph at the same time?

[github-actions]

This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!

[github-actions]

This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant. Thank you!