[Bug]: VLLM + tritonserver #4695
Description
Your current environment
Python platform: Linux-5.10.213-201.855.amzn2.x86_64-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.3.107
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA A100-SXM4-80GB
GPU 1: NVIDIA A100-SXM4-80GB
GPU 2: NVIDIA A100-SXM4-80GB
GPU 3: NVIDIA A100-SXM4-80GB
GPU 4: NVIDIA A100-SXM4-80GB
GPU 5: NVIDIA A100-SXM4-80GB
GPU 6: NVIDIA A100-SXM4-80GB
GPU 7: NVIDIA A100-SXM4-80GB
Nvidia driver version: 535.161.08
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, 48 bits virtual
Byte Order: Little Endian
CPU(s): 96
On-line CPU(s) list: 0-95
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8275CL CPU @ 3.00GHz
CPU family: 6
Model: 85
Thread(s) per core: 2
Core(s) per socket: 24
Socket(s): 2
Stepping: 7
BogoMIPS: 5999.99
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 aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves ida arat pku ospke
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 1.5 MiB (48 instances)
L1i cache: 1.5 MiB (48 instances)
L2 cache: 48 MiB (48 instances)
L3 cache: 71.5 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-23,48-71
NUMA node1 CPU(s): 24-47,72-95
Vulnerability Gather data sampling: Unknown: Dependent on hypervisor status
Vulnerability Itlb multihit: KVM: Mitigation: VMX unsupported
Vulnerability L1tf: Mitigation; PTE Inversion
Vulnerability Mds: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Meltdown: Mitigation; PTI
Vulnerability Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed: Vulnerable
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines, STIBP disabled, RSB filling
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] torch==2.3.0
[pip3] triton==2.3.0
[pip3] tritonclient==2.44.0
[conda] Could not collectROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.4.2
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV12 NV12 NV12 NV12 NV12 NV12 NV12 0-23,48-71 0 N/A
GPU1 NV12 X NV12 NV12 NV12 NV12 NV12 NV12 0-23,48-71 0 N/A
GPU2 NV12 NV12 X NV12 NV12 NV12 NV12 NV12 0-23,48-71 0 N/A
GPU3 NV12 NV12 NV12 X NV12 NV12 NV12 NV12 0-23,48-71 0 N/A
GPU4 NV12 NV12 NV12 NV12 X NV12 NV12 NV12 24-47,72-95 1 N/A
GPU5 NV12 NV12 NV12 NV12 NV12 X NV12 NV12 24-47,72-95 1 N/A
GPU6 NV12 NV12 NV12 NV12 NV12 NV12 X NV12 24-47,72-95 1 N/A
GPU7 NV12 NV12 NV12 NV12 NV12 NV12 NV12 X 24-47,72-95 1 N/A
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
🐛 Describe the bug
We run tritonserver + vLLM backend (docker image for tritonserver = tritonserver:24.02-vllm-python-py3). With vLLM = 0.3.2, we don't see any issue.
With both vLLM = 0.4.0post1 and vLLM=0.4.2, very quickly after starting triton server, it becomes unresponsive, and we see in the logs:
I0508 20:24:09.727326 152 model.py:284] [vllm] Error generating stream: Background loop has errored already.
[rank0]:[E ProcessGroupNCCL.cpp:563] [Rank 0] Watchdog caught collective operation timeout: WorkNCCL(SeqNum=1196, OpType=GATHER, NumelIn=12000, NumelOut=12000, Timeout(ms)=600000) ran for 600073 milliseconds before timing out.
[rank0]:[E ProcessGroupNCCL.cpp:1537] [PG 1 Rank 0] Timeout at NCCL work: 1196, last enqueued NCCL work: 1196, last completed NCCL work: 1195.
[rank0]:[E ProcessGroupNCCL.cpp:577] [Rank 0] Some NCCL operations have failed or timed out. Due to the asynchronous nature of CUDA kernels, subsequent GPU operations might run on corrupted/incomplete data.
[rank0]:[E ProcessGroupNCCL.cpp:583] [Rank 0] To avoid data inconsistency, we are taking the entire process down.
[rank0]:[E ProcessGroupNCCL.cpp:1414] [PG 1 Rank 0] Process group watchdog thread terminated with exception: [Rank 0] Watchdog caught collective operation timeout: WorkNCCL(SeqNum=1196, OpType=GATHER, NumelIn=12000, NumelOut=12000, Timeout(ms)=600000) ran for 600073 milliseconds before timing out.
Exception raised from checkTimeout at ../torch/csrc/distributed/c10d/ProcessGroupNCCL.cpp:565 (most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::string) + 0x57 (0x7f36b5f7a897 in /usr/local/lib/python3.10/dist-packages/torch/lib/libc10.so)
frame #1: c10d::ProcessGroupNCCL::WorkNCCL::checkTimeout(std::optional<std::chrono::duration<long, std::ratio<1l, 1000l> > >) + 0x1d2 (0x7f366a27b1b2 in /usr/local/lib/python3.10/dist-packages/torch/lib/libtorch_cuda.so)
frame #2: c10d::ProcessGroupNCCL::watchdogHandler() + 0x1a0 (0x7f366a27ffd0 in /usr/local/lib/python3.10/dist-packages/torch/lib/libtorch_cuda.so)
frame #3: c10d::ProcessGroupNCCL::ncclCommWatchdog() + 0x10c (0x7f366a28131c in /usr/local/lib/python3.10/dist-packages/torch/lib/libtorch_cuda.so)
frame #4: + 0xdc253 (0x7f36c20d9253 in /usr/lib/x86_64-linux-gnu/libstdc++.so.6)
frame #5: + 0x94ac3 (0x7f36c1e68ac3 in /usr/lib/x86_64-linux-gnu/libc.so.6)
frame #6: + 0x126850 (0x7f36c1efa850 in /usr/lib/x86_64-linux-gnu/libc.so.6)