[Bug]: how to use full cuda graph option in v1? #18520
Description
Your current environment
PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 4.0.0
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-3.10.0-1160.71.1.el7.x86_64-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.4.99
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H20
GPU 1: NVIDIA H20
GPU 2: NVIDIA H20
GPU 3: NVIDIA H20
GPU 4: NVIDIA H20
GPU 5: NVIDIA H20
GPU 6: NVIDIA H20
GPU 7: NVIDIA H20
Nvidia driver version: 535.216.03
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.0.0
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): 240
On-line CPU(s) list: 0-239
Vendor ID: GenuineIntel
Model name: INTEL(R) XEON(R) PLATINUM 8580
CPU family: 6
Model: 207
Thread(s) per core: 2
Core(s) per socket: 60
Socket(s): 2
Stepping: 2
Frequency boost: enabled
CPU max MHz: 2001.0000
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 aperfmperf eagerfpu pni pclmulqdq dtes64 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 epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_pt cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq cldemote movdiri movdir64b md_clear pconfig spec_ctrl intel_stibp flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 5.6 MiB (120 instances)
L1i cache: 3.8 MiB (120 instances)
L2 cache: 240 MiB (120 instances)
L3 cache: 600 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-59,120-179
NUMA node1 CPU(s): 60-119,180-239
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; Load fences, usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] mypy_extensions==1.1.0
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-cusparselt-cu12==0.6.2
[pip3] nvidia-dali-cuda120==1.35.0
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] nvidia-pyindex==1.0.9
[pip3] onnx==1.15.0rc2
[pip3] optree==0.15.0
[pip3] pynvml==11.4.1
[pip3] pytorch-quantization==2.1.2
[pip3] pytorch-triton==2.2.0+e28a256d7
[pip3] pyzmq==25.1.2
[pip3] torch==2.6.0
[pip3] torch_memory_saver==0.0.5
[pip3] torch-tensorrt==2.3.0a0
[pip3] torchao==0.10.0
[pip3] torchaudio==2.6.0
[pip3] torchdata==0.7.1a0
[pip3] torchtext==0.17.0a0
[pip3] torchvision==0.21.0
[pip3] transformers==4.51.1
[pip3] triton==3.2.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.8.5.dev665+gd4154c35a.d20250522 (git sha: d4154c3, date: 20250522)
vLLM Build Flags:
CUDA Archs: 9.0+PTX; ROCm: Disabled; Neuron: 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 NODE NODE NODE NODE NODE NODE SYS SYS SYS SYS 0-59,120-179 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 PIX PIX NODE NODE NODE NODE NODE NODE SYS SYS SYS SYS 0-59,120-179 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE NODE NODE PIX PIX NODE NODE SYS SYS SYS SYS 0-59,120-179 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE NODE NODE NODE PIX PIX NODE NODE SYS SYS SYS SYS 0-59,120-179 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS SYS SYS SYS SYS PIX PIX NODE NODE 60-119,180-239 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS SYS SYS SYS SYS PIX PIX NODE NODE 60-119,180-239 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS SYS SYS SYS SYS NODE NODE PIX PIX 60-119,180-239 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS SYS SYS SYS SYS NODE NODE PIX PIX 60-119,180-239 1 N/A
NIC0 PIX PIX NODE NODE SYS SYS SYS SYS X PIX NODE NODE NODE NODE NODE NODE SYS SYS SYS SYS
NIC1 PIX PIX NODE NODE SYS SYS SYS SYS PIX X NODE NODE NODE NODE NODE NODE SYS SYS SYS SYS
NIC2 NODE NODE NODE NODE SYS SYS SYS SYS NODE NODE X PIX NODE NODE NODE NODE SYS SYS SYS SYS
NIC3 NODE NODE NODE NODE SYS SYS SYS SYS NODE NODE PIX X NODE NODE NODE NODE SYS SYS SYS SYS
NIC4 NODE NODE PIX PIX SYS SYS SYS SYS NODE NODE NODE NODE X PIX NODE NODE SYS SYS SYS SYS
NIC5 NODE NODE PIX PIX SYS SYS SYS SYS NODE NODE NODE NODE PIX X NODE NODE SYS SYS SYS SYS
NIC6 NODE NODE NODE NODE SYS SYS SYS SYS NODE NODE NODE NODE NODE NODE X PIX SYS SYS SYS SYS
NIC7 NODE NODE NODE NODE SYS SYS SYS SYS NODE NODE NODE NODE NODE NODE PIX X SYS SYS SYS SYS
NIC8 SYS SYS SYS SYS PIX PIX NODE NODE SYS SYS SYS SYS SYS SYS SYS SYS X PIX NODE NODE
NIC9 SYS SYS SYS SYS PIX PIX NODE NODE SYS SYS SYS SYS SYS SYS SYS SYS PIX X NODE NODE
NIC10 SYS SYS SYS SYS NODE NODE PIX PIX SYS SYS SYS SYS SYS SYS SYS SYS NODE NODE X PIX
NIC11 SYS SYS SYS SYS NODE NODE PIX PIX SYS SYS SYS SYS SYS SYS SYS SYS NODE NODE PIX 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
NVIDIA_VISIBLE_DEVICES=GPU-c2e1e16d-ac6b-b360-f2e1-82a237c806e2,GPU-d3d486ae-6db8-f1cc-777d-3fae2f02f911,GPU-51de713f-bce7-ebb2-2c2b-6ffee1a049c3,GPU-55793d3c-d315-2ab1-7617-c1d9dafd0330,GPU-7244c04a-59a1-ac0f-66ff-8d643522055c,GPU-35456765-eb3c-15e8-5f1c-7c4773c30c0f,GPU-f42623e1-2400-9e48-03e8-7d816ea31a94,GPU-427a805c-be02-5c66-ddac-f8967cfa8e31
CUBLAS_VERSION=12.4.2.65
NVIDIA_REQUIRE_CUDA=cuda>=9.0
CUDA_CACHE_DISABLE=1
TORCH_CUDA_ARCH_LIST=9.0+PTX
NCCL_VERSION=2.20.5
NVIDIA_DRIVER_CAPABILITIES=compute,utility,video
NVIDIA_PRODUCT_NAME=PyTorch
NCCL_WORK_FIFO_DEPTH=4194304
CUDA_VERSION=12.4.0.041
PYTORCH_VERSION=2.3.0a0+40ec155e58
PYTORCH_BUILD_NUMBER=0
CUDNN_VERSION=9.0.0.306+cuda12.3
PYTORCH_HOME=/opt/pytorch/pytorch
LD_LIBRARY_PATH=/usr/local/cuda/compat/lib.real:/usr/local/lib/python3.10/dist-packages/torch/lib:/usr/local/lib/python3.10/dist-packages/torch_tensorrt/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
NVIDIA_BUILD_ID=85286408
CUDA_DRIVER_VERSION=550.54.14
PYTORCH_BUILD_VERSION=2.3.0a0+40ec155e58
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
VLLM_LOGGING_LEVEL=DEBUG
VLLM_HOST_IP=10.248.7.38
CUDA_MODULE_LOADING=LAZY
NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=
NVIDIA_PYTORCH_VERSION=24.03
TORCH_ALLOW_TF32_CUBLAS_OVERRIDE=1
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
🐛 Describe the bug
vllm serve Qwen2.5-1.5B-Instruct --compilation-config "{'full_cuda_graph': True}"
1.--compilation-config "{'full_cuda_graph': True}" cannot be added and will report vllm serve: error: argument --compilation-config/-O: invalid value: "{'full_cuda_graph': True}"
2.The output becomes messy and meaningless with manually set full_cuda_graph=True in config.py.
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.