[Bug]: Device Type HPU is not support when server parameters are changed

[nageshdn]

Your current environment

The output of `python collect_env.py`

root@node1:/workspace/vllm# python collect_env.py
INFO 01-29 16:50:57 __init__.py:192] 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-5.15.0-121-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: 8x 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):                               192
On-line CPU(s) list:                  0-191
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Platinum 8468
CPU family:                           6
Model:                                143
Thread(s) per core:                   2
Core(s) per socket:                   48
Socket(s):                            2
Stepping:                             8
BogoMIPS:                             4200.00
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 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 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:                            4.5 MiB (96 instances)
L1i cache:                            3 MiB (96 instances)
L2 cache:                             192 MiB (96 instances)
L3 cache:                             210 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126,128,130,132,134,136,138,140,142,144,146,148,150,152,154,156,158,160,162,164,166,168,170,172,174,176,178,180,182,184,186,188,190
NUMA node1 CPU(s):                    1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127,129,131,133,135,137,139,141,143,145,147,149,151,153,155,157,159,161,163,165,167,169,171,173,175,177,179,181,183,185,187,189,191
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 Reg file data sampling: 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 / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

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==26.2.0
[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==4.48.1
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.3.dev2059+g8642d892
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
Could not collect

VLLM_TARGET_DEVICE=hpu
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

Model Input Dumps

No response

🐛 Describe the bug

Running vLLM provided benchmarks causes the given below error,

Input command:
Server command: python3 -m vllm.entrypoints.openai.api_server --model meta-llama/Meta-Llama-3.1-8B-Instruct --tensor-parallel-size 1 --swap-space 16 --disable-log-stats --disable-log-requests --load-format dummy

Note, this Server command is standard vllm server parameters present in Habana AI at vllm/.buildkite/nightly-benchmarks/tests/serving-tests.json

Output result:
etected flags: [-compile_one_hot -cpu -fp32_softmax +fsdpa -gaudi +gaudi2 -gaudi3]
ERROR 01-29 16:41:43 engine.py:381] Device type HPU is not supported for torch.Generator() api.
ERROR 01-29 16:41:43 engine.py:381] Traceback (most recent call last):
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/engine/multiprocessing/engine.py", line 372, in run_mp_engine
ERROR 01-29 16:41:43 engine.py:381] engine = MQLLMEngine.from_engine_args(engine_args=engine_args,
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/engine/multiprocessing/engine.py", line 120, in from_engine_args
ERROR 01-29 16:41:43 engine.py:381] return cls(ipc_path=ipc_path,
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/engine/multiprocessing/engine.py", line 72, in init
ERROR 01-29 16:41:43 engine.py:381] self.engine = LLMEngine(*args, **kwargs)
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/engine/llm_engine.py", line 271, in init
ERROR 01-29 16:41:43 engine.py:381] self.model_executor = executor_class(vllm_config=vllm_config, )
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/executor/executor_base.py", line 49, in init
ERROR 01-29 16:41:43 engine.py:381] self._init_executor()
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/executor/uniproc_executor.py", line 40, in _init_executor
ERROR 01-29 16:41:43 engine.py:381] self.collective_rpc("load_model")
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/executor/uniproc_executor.py", line 51, in collective_rpc
ERROR 01-29 16:41:43 engine.py:381] answer = run_method(self.driver_worker, method, args, kwargs)
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/utils.py", line 2305, in run_method
ERROR 01-29 16:41:43 engine.py:381] return func(*args, **kwargs)
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/worker/hpu_worker.py", line 219, in load_model
ERROR 01-29 16:41:43 engine.py:381] self.model_runner.load_model()
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/worker/hpu_model_runner.py", line 708, in load_model
ERROR 01-29 16:41:43 engine.py:381] self.model = get_model(vllm_config=self.vllm_config)
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/model_executor/model_loader/init.py", line 12, in get_model
ERROR 01-29 16:41:43 engine.py:381] return loader.load_model(vllm_config=vllm_config)
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/model_executor/model_loader/loader.py", line 439, in load_model
ERROR 01-29 16:41:43 engine.py:381] initialize_dummy_weights(model)
ERROR 01-29 16:41:43 engine.py:381] File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev2059+g8642d892.gaudi000-py3.10.egg/vllm/model_executor/model_loader/weight_utils.py", line 647, in initialize_dummy_weights
ERROR 01-29 16:41:43 engine.py:381] generator = torch.Generator(device=param.data.device)
ERROR 01-29 16:41:43 engine.py:381] RuntimeError: Device type HPU is not supported for torch.Generator() api.

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.

[pi314ever]

There is a fix pending in #747 which provides a workaround for --load-format=dummy on HPU.

[PatrykWo]

@nageshdn please verify if that fix resolving the issue.