[Bug]: Exception ignored in: LLMEngine and ExecutorBase: TypeError: NoneType object is not callable

[malkomes]

Your current environment

The output of `python collect_env.py`

INFO 02-26 18:09:57 __init__.py:199] Automatically detected platform hpu.
Collecting environment information...
PyTorch version: 2.5.1a0+git6fc067b
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.5 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.22.1
Libc version: glibc-2.35

Python version: 3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-112-generic-x86_64-with-glibc2.35
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HPU devices: 1x HL-225
HPU driver version: 1.19.1-6f47ddd
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):                             20
On-line CPU(s) list:                0-19
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Platinum 8380 CPU @ 2.30GHz
CPU family:                         6
Model:                              106
Thread(s) per core:                 2
Core(s) per socket:                 5
Socket(s):                          2
Stepping:                           6
BogoMIPS:                           4589.21
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 cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid fsrm md_clear arch_capabilities
Virtualization:                     VT-x
Hypervisor vendor:                  KVM
Virtualization type:                full
L1d cache:                          480 KiB (10 instances)
L1i cache:                          320 KiB (10 instances)
L2 cache:                           12.5 MiB (10 instances)
L3 cache:                           60 MiB (1 instance)
NUMA node(s):                       1
NUMA node0 CPU(s):                  0-19
Vulnerability Gather data sampling: Unknown: Dependent on hypervisor status
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
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; BHI Syscall hardening, KVM SW loop
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Mitigation; TSX disabled

Versions of relevant libraries:
[pip3] habana-torch-dataloader==1.19.1.26
[pip3] habana-torch-plugin==1.19.1.26
[pip3] numpy==1.26.4
[pip3] pynvml==8.0.4
[pip3] pytorch-lightning==2.5.0.post0
[pip3] pyzmq==26.2.1
[pip3] torch==2.5.1a0+git6fc067b
[pip3] torch_tb_profiler==0.4.0
[pip3] torchaudio==2.5.1a0+1661daf
[pip3] torchdata==0.9.0+d4bb3e6
[pip3] torchmetrics==1.6.1
[pip3] torchtext==0.18.0a0+9bed85d
[pip3] torchvision==0.20.1a0+3ac97aa
[pip3] transformers==4.49.0.dev0
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.1.dev5285+g2ec4d06.d20250226 (git sha: 2ec4d06.d20250226
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
Could not collect

LD_LIBRARY_PATH=/usr/local/lib/python3.10/dist-packages/cv2/../../lib64:/opt/habanalabs/libfabric-1.22.0/lib:/opt/amazon/openmpi/lib:/usr/lib/habanalabs:
NCCL_CUMEM_ENABLE=0
TORCHINDUCTOR_COMPILE_THREADS=1

🐛 Describe the bug

Looks like any call to the Engine is triggering the following exception:

Exception ignored in: <function LLMEngine.__del__ at 0x7fd9ae501630>
Traceback (most recent call last):
  File "/workspace/vllm/vllm/engine/llm_engine.py", line 503, in __del__
  File "/workspace/vllm/vllm/executor/uniproc_executor.py", line 68, in shutdown
  File "/workspace/vllm/vllm/executor/uniproc_executor.py", line 58, in collective_rpc
TypeError: 'NoneType' object is not callable
Exception ignored in: <function ExecutorBase.__del__ at 0x7fd9b0d889d0>
Traceback (most recent call last):
  File "/workspace/vllm/vllm/executor/executor_base.py", line 235, in __del__
  File "/workspace/vllm/vllm/executor/uniproc_executor.py", line 68, in shutdown
  File "/workspace/vllm/vllm/executor/uniproc_executor.py", line 58, in collective_rpc
TypeError: 'NoneType' object is not callable

To reproduce, I'm on the latest commit 020bd35dee1d302723ad40ff5e962fa41782aba and just ran

python examples/lora_inference_hpu.py

The code outputs the expected information but ends with the exception above.

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.

[michalkuligowski]

Hi @malkomes Thank you for the ticket, judging from your output from collect_env.py which shows
"vLLM Version: 0.1.dev5285+g2ec4d06.d20250226 "
which is not in line with the versions that were released and does not reflect the sha you mentioned - 020bd35, that there is something wrong with the installation on your environment.
Please refer to Build and Install section in https://github.com/HabanaAI/vllm-fork/releases/tag/v0.6.6.post1%2BGaudi-1.20.0 for latest release installation.

[malkomes]

Oh yes, my report is for the current habana_main, which is a development version. As of two weeks ago, I wasn't seen this issue. If the issues are just for the release I can close this (: