search

HabanaAI / vllm-fork

A high-throughput and memory-efficient inference and serving engine for LLMs
https://docs.vllm.ai
Apache License 2.0
38 stars 47 forks source link

[Bug]: Device type HPU is not supported for torch.Generator() api #183

Open sungwook-son opened 2 months ago

sungwook-son commented 2 months ago

Your current environment

PyTorch version: 2.3.1a0+git4989238
Is debug build: False
CUDA used to build PyTorch: None
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 3.30.1
Libc version: glibc-2.35

Python version: 3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-105-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
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):                             160
On-line CPU(s) list:                0-159
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:                 40
Socket(s):                          2
Stepping:                           6
CPU max MHz:                        3400.0000
CPU min MHz:                        800.0000
BogoMIPS:                           4600.00
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 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 invpcid_single intel_ppin 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 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          3.8 MiB (80 instances)
L1i cache:                          2.5 MiB (80 instances)
L2 cache:                           100 MiB (80 instances)
L3 cache:                           120 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-39,80-119
NUMA node1 CPU(s):                  40-79,120-159
Vulnerability Gather data sampling: Mitigation; Microcode
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable
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] habana-torch-dataloader==1.17.0.495
[pip3] habana-torch-plugin==1.17.0.495
[pip3] numpy==1.23.5
[pip3] pytorch-lightning==2.3.3
[pip3] pyzmq==26.1.0
[pip3] torch==2.3.1a0+git4989238
[pip3] torch_tb_profiler==0.4.0
[pip3] torchaudio==2.3.0+952ea74
[pip3] torchdata==0.7.1+5e6f7b7
[pip3] torchmetrics==1.4.0.post0
[pip3] torchtext==0.18.0a0+9bed85d
[pip3] torchvision==0.18.1a0+fe70bc8
[pip3] transformers==4.43.3
[pip3] triton==3.0.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.3.post1@c0984334c495762b10ee37dc817afad9fec0ef57
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
Could not collect

🐛 Describe the bug

Error screenshot image

Task being performed: I want to measure model performance using lm-evaluation-harness and use vLLM as a backend server. When launching vLLM with vllm.entrypoints.openai.api_server, it seems like it is calling the lines below which raises Device type HPU is not supported for torch.Generator() api error.

https://github.com/HabanaAI/vllm-fork/blob/c0984334c495762b10ee37dc817afad9fec0ef57/vllm/model_executor/sampling_metadata.py#L218-L222

I wanted to ask if it is an expected behavior.

Script used to run vLLM

export MODEL_NAME="meta-llama/Meta-Llama-3-8B"

python3 -m vllm.entrypoints.openai.api_server \
        --model $MODEL_NAME \
        --gpu-memory-utilization 0.95 \
        --tensor-parallel-size  1   \
        --dtype bfloat16 \
        --kv-cache-dtype auto \
        --swap-space  32  \
        --max-num-seqs 128 \
        --block-size 128 \
        --host 0.0.0.0 \
        --port  9915

Script used to run lm-eval


git clone https://github.com/EleutherAI/lm-evaluation-harness.git
cd lm-evaluation-harness && pip install -e ".[api]"

lm_eval --model local-completions \
    --tasks mmlu \
    --model_args "model=meta-llama/Meta-Llama-3-8B,base_url=http://localhost:9915/v1/completions,num_concurrent=16,max_retries=3,tokenized_requests=False" \
  --verbosity DEBUG --log_samples --output_path test/

Same config running on H100 image

libinta commented 1 week ago

@sungwook-son please test with PR https://github.com/HabanaAI/vllm-fork/pull/246/files to see if your issue is resolved>