vllm icon indicating copy to clipboard operation
vllm copied to clipboard

Published 20 hours ago • verified publisher icon vllm-project

[Bug]: Nccl Test Error

Open zhaotyer opened this issue 1 month ago • 19 comments

Your current environment

The output of `python collect_env.py` 
Collecting environment information...
PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
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: Could not collect
Libc version: glibc-2.35

Python version: 3.12.8 (main, Dec  4 2024, 08:54:12) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-97-generic-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 H20
GPU 1: NVIDIA H20

Nvidia driver version: 550.54.14
cuDNN version: Could not collect
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):                             224
On-line CPU(s) list:                0-223
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Platinum 8480+
CPU family:                         6
Model:                              143
Thread(s) per core:                 2
Core(s) per socket:                 56
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 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 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req 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 amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          5.3 MiB (112 instances)
L1i cache:                          3.5 MiB (112 instances)
L2 cache:                           224 MiB (112 instances)
L3 cache:                           210 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-55,112-167
NUMA node1 CPU(s):                  56-111,168-223
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 Retbleed:             Not affected
Vulnerability Spec rstack overflow: 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] flashinfer==0.1.6+cu121torch2.4
[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-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] pyzmq==26.2.0
[pip3] torch==2.5.1
[pip3] torchvision==0.20.1
[pip3] transformers==4.47.1
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: N/A
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    GPU1    NIC0    NIC1    NIC2    NIC3    NIC4    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV18    SYS     PIX     SYS     SYS     SYS     0-55,112-167    0               N/A
GPU1    NV18     X      SYS     SYS     SYS     SYS     SYS     0-55,112-167    0               N/A
NIC0    SYS     SYS      X      SYS     SYS     SYS     SYS
NIC1    PIX     SYS     SYS      X      SYS     SYS     SYS
NIC2    SYS     SYS     SYS     SYS      X      SYS     SYS
NIC3    SYS     SYS     SYS     SYS     SYS      X      SYS
NIC4    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

Model Input Dumps

No response

🐛 Describe the bug

vLLM NCCL test failed test image is: /vllm/vllm-openai:latest vllm version is: 0.6.6.post1 docker commad is:

docker run -id --name test --network host  --ipc=host  -e NVIDIA_VISIBLE_DEVICES=2,3 -v `pwd`:/models --entrypoint=bash vllm/vllm-openai:latest

test.py: https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#incorrect-hardware-driver NCCL_DEBUG=TRACE torchrun --nproc-per-node=2 test.py

PyTorch NCCL is successful!
PyTorch GLOO is successful!
PyTorch GLOO is successful!
INFO 01-13 04:05:17 utils.py:918] Found nccl from library libnccl.so.2
INFO 01-13 04:05:17 utils.py:918] Found nccl from library libnccl.so.2
INFO 01-13 04:05:17 pynccl.py:69] vLLM is using nccl==2.21.5
INFO 01-13 04:05:17 pynccl.py:69] vLLM is using nccl==2.21.5
bm-22075ry:1259:1259 [0] NCCL INFO Using non-device net plugin version 0
bm-22075ry:1260:1260 [1] NCCL INFO Using non-device net plugin version 0
bm-22075ry:1259:1259 [0] NCCL INFO Using network Socket
bm-22075ry:1260:1260 [1] NCCL INFO Using network Socket
bm-22075ry:1259:1259 [0] NCCL INFO ncclCommInitRank comm 0xc4cbfc0 rank 0 nranks 2 cudaDev 0 nvmlDev 0 busId 48000 commId 0x9ff7e868477ca4f8 - Init START
bm-22075ry:1260:1260 [1] NCCL INFO ncclCommInitRank comm 0xbea9880 rank 1 nranks 2 cudaDev 1 nvmlDev 1 busId 5a000 commId 0x9ff7e868477ca4f8 - Init START
bm-22075ry:1259:1259 [0] NCCL INFO MNNVL busId 0x48000 fabric UUID 0.0 cliqueId 0x0 state 3 healthMask 0x0
bm-22075ry:1260:1260 [1] NCCL INFO MNNVL busId 0x5a000 fabric UUID 0.0 cliqueId 0x0 state 3 healthMask 0x0
bm-22075ry:1259:1259 [0] NCCL INFO Setting affinity for GPU 0 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff
bm-22075ry:1260:1260 [1] NCCL INFO Setting affinity for GPU 1 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff
bm-22075ry:1260:1260 [1] NCCL INFO comm 0xbea9880 rank 1 nRanks 2 nNodes 1 localRanks 2 localRank 1 MNNVL 0
bm-22075ry:1259:1259 [0] NCCL INFO comm 0xc4cbfc0 rank 0 nRanks 2 nNodes 1 localRanks 2 localRank 0 MNNVL 0
bm-22075ry:1259:1259 [0] NCCL INFO Channel 00/24 :    0   1
bm-22075ry:1260:1260 [1] NCCL INFO Trees [0] -1/-1/-1->1->0 [1] -1/-1/-1->1->0 [2] -1/-1/-1->1->0 [3] -1/-1/-1->1->0 [4] -1/-1/-1->1->0 [5] -1/-1/-1->1->0 [6] 0/-1/-1->1->-1 [7] 0/-1/-1->1->-1 [8] 0/-1/-1->1->-1 [9] 0/-1/-1->1->-1 [10] 0/-1/-1->1->-1 [11] 0/-1/-1->1->-1 [12] -1/-1/-1->1->0 [13] -1/-1/-1->1->0 [14] -1/-1/-1->1->0 [15] -1/-1/-1->1->0 [16] -1/-1/-1->1->0 [17] -1/-1/-1->1->0 [18] 0/-1/-1->1->-1 [19] 0/-1/-1->1->-1 [20] 0/-1/-1->1->-1 [21] 0/-1/-1->1->-1 [22] 0/-1/-1->1->-1 [23] 0/-1/-1->1->-1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 01/24 :    0   1
bm-22075ry:1260:1260 [1] NCCL INFO P2P Chunksize set to 524288
bm-22075ry:1259:1259 [0] NCCL INFO Channel 02/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 03/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 04/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 05/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 06/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 07/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 08/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 09/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 10/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 11/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 12/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 13/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 14/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 15/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 16/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 17/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 18/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 19/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 20/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 21/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 22/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Channel 23/24 :    0   1
bm-22075ry:1259:1259 [0] NCCL INFO Trees [0] 1/-1/-1->0->-1 [1] 1/-1/-1->0->-1 [2] 1/-1/-1->0->-1 [3] 1/-1/-1->0->-1 [4] 1/-1/-1->0->-1 [5] 1/-1/-1->0->-1 [6] -1/-1/-1->0->1 [7] -1/-1/-1->0->1 [8] -1/-1/-1->0->1 [9] -1/-1/-1->0->1 [10] -1/-1/-1->0->1 [11] -1/-1/-1->0->1 [12] 1/-1/-1->0->-1 [13] 1/-1/-1->0->-1 [14] 1/-1/-1->0->-1 [15] 1/-1/-1->0->-1 [16] 1/-1/-1->0->-1 [17] 1/-1/-1->0->-1 [18] -1/-1/-1->0->1 [19] -1/-1/-1->0->1 [20] -1/-1/-1->0->1 [21] -1/-1/-1->0->1 [22] -1/-1/-1->0->1 [23] -1/-1/-1->0->1
bm-22075ry:1259:1259 [0] NCCL INFO P2P Chunksize set to 524288
bm-22075ry:1260:1260 [1] NCCL INFO Channel 00/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 01/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 01/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 02/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 03/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 04/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 05/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 06/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 07/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 08/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 09/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 09/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 10/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 11/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 12/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 13/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 14/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 15/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 16/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 16/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 17/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 17/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 18/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 18/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 19/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 19/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 20/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 20/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 21/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 21/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 22/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 22/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Channel 23/0 : 1[1] -> 0[0] via P2P/CUMEM
bm-22075ry:1259:1259 [0] NCCL INFO Channel 23/0 : 0[0] -> 1[1] via P2P/CUMEM
bm-22075ry:1260:1260 [1] NCCL INFO Connected all rings
bm-22075ry:1260:1260 [1] NCCL INFO Connected all trees
bm-22075ry:1260:1260 [1] NCCL INFO threadThresholds 8/8/64 | 16/8/64 | 512 | 512
bm-22075ry:1260:1260 [1] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
bm-22075ry:1259:1259 [0] NCCL INFO Connected all rings
bm-22075ry:1259:1259 [0] NCCL INFO Connected all trees
bm-22075ry:1259:1259 [0] NCCL INFO threadThresholds 8/8/64 | 16/8/64 | 512 | 512
bm-22075ry:1259:1259 [0] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
bm-22075ry:1260:1260 [1] NCCL INFO ncclCommInitRank comm 0xbea9880 rank 1 nranks 2 cudaDev 1 nvmlDev 1 busId 5a000 commId 0x9ff7e868477ca4f8 - Init COMPLETE
bm-22075ry:1259:1259 [0] NCCL INFO ncclCommInitRank comm 0xc4cbfc0 rank 0 nranks 2 cudaDev 0 nvmlDev 0 busId 48000 commId 0x9ff7e868477ca4f8 - Init COMPLETE
[rank0]: Traceback (most recent call last):
[rank0]:   File "/vllm-workspace/test.py", line 44, in <module>
[rank0]:     assert value == world_size, f"Expected {world_size}, got {value}"
[rank0]:            ^^^^^^^^^^^^^^^^^^^
[rank0]: AssertionError: Expected 2, got 1.0
[rank1]: Traceback (most recent call last):
[rank1]:   File "/vllm-workspace/test.py", line 44, in <module>
[rank1]:     assert value == world_size, f"Expected {world_size}, got {value}"
[rank1]:            ^^^^^^^^^^^^^^^^^^^
[rank1]: AssertionError: Expected 2, got 1.0
bm-22075ry:1260:1272 [1] NCCL INFO [Service thread] Connection closed by localRank 1
[rank0]:[W113 04:05:19.919179277 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present,  but this warning has only been added since PyTorch 2.4 (function operator())
bm-22075ry:1259:1273 [0] NCCL INFO [Service thread] Connection closed by localRank 0
bm-22075ry:1260:1301 [1] NCCL INFO comm 0x8891ff0 rank 1 nranks 2 cudaDev 1 busId 5a000 - Abort COMPLETE
bm-22075ry:1259:1302 [0] NCCL INFO comm 0x8eb37b0 rank 0 nranks 2 cudaDev 0 busId 48000 - Abort COMPLETE
W0113 04:05:20.165000 1194 torch/distributed/elastic/multiprocessing/api.py:897] Sending process 1259 closing signal SIGTERM
E0113 04:05:20.197000 1194 torch/distributed/elastic/multiprocessing/api.py:869] failed (exitcode: 1) local_rank: 1 (pid: 1260) of binary: /usr/bin/python3
Traceback (most recent call last):
  File "/usr/local/bin/torchrun", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
    return f(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/distributed/run.py", line 919, in main
    run(args)
  File "/usr/local/lib/python3.12/dist-packages/torch/distributed/run.py", line 910, in run
    elastic_launch(
  File "/usr/local/lib/python3.12/dist-packages/torch/distributed/launcher/api.py", line 138, in __call__
    return launch_agent(self._config, self._entrypoint, list(args))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/distributed/launcher/api.py", line 269, in launch_agent
    raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
test.py FAILED
------------------------------------------------------------
Failures:
  <NO_OTHER_FAILURES>
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
  time      : 2025-01-13_04:05:20
  host      : bm-22075ry
  rank      : 1 (local_rank: 1)
  exitcode  : 1 (pid: 1260)
  error_file: <N/A>
  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html

Is there a problem with the test.py script? vllm serve /models/Llama-3.1-8B-Instruct/ -tp 2 Execution is normal I used test.py to test the communication problem because I deployed deepseek-v3 on two machines using lws, but it got stuck at generating GPU P2P access cache in /root/.cache/vllm/gpu_p2p_access_cache_for_*json.

Before submitting a new issue...

  • [X] 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.

zhaotyer avatar Jan 13 '25 12:01 zhaotyer