Illegal instruction (core dumped)

[leoneyar]

##Running Scripts：
#!/bin/bash
model="/llm/models/DeepSeek-R1-Distill-Qwen-7B"
served_model_name="deepseek-7b"

python -m ipex_llm.vllm.cpu.entrypoints.openai.api_server
--served-model-name $served_model_name
--port 8001
--model $model
--trust-remote-code
--device cpu
--dtype float16
--enforce-eager
--load-in-low-bit "none"
--max-model-len 4096
--max-num-batched-tokens 10240
--max-num-seqs 12
--tensor-parallel-size 1

##error message
start-vllm-service.sh: line 18: 1669 Illegal instruction (core dumped) python -m ipex_llm.vllm.cpu.entrypoints.openai.api_server --served-model-name $served_model_name --port 8001 --model $model --trust-remote-code --device cpu --dtype float16 --enforce-eager --load-in-low-bit "none" --max-model-len 4096 --max-num-batched-tokens 10240 --max-num-seqs 12 --tensor-parallel-size 1

##cpu message
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 80
On-line CPU(s) list: 0-79
Thread(s) per core: 2
Core(s) per socket: 10
Socket(s): 4
NUMA node(s): 4
Vendor ID: GenuineIntel
CPU family: 6
Model: 62
Model name: Intel(R) Xeon(R) CPU E7-4830 v2 @ 2.20GHz
Stepping: 7
CPU MHz: 1203.662
CPU max MHz: 2200.0000
CPU min MHz: 1200.0000
BogoMIPS: 4389.39
Virtualization: VT-x
L1d cache: 32K
L1i cache: 32K
L2 cache: 256K
L3 cache: 20480K
NUMA node0 CPU(s): 0-9,40-49
NUMA node1 CPU(s): 10-19,50-59
NUMA node2 CPU(s): 20-29,60-69
NUMA node3 CPU(s): 30-39,70-79
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 arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm epb intel_ppin ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms xsaveopt dtherm arat pln pts md_clear spec_ctrl intel_stibp flush_l1d

[xiangyuT]

Hi @leoneyar,

It seems that the none setting for load-in-low-bit in your scripts is invalid for this command. I suggest trying the settings we provide:

python -m ipex_llm.vllm.cpu.entrypoints.openai.api_server \
  --served-model-name $served_model_name \
  --port 8000 \
  --model $model \
  --trust-remote-code \
  --device cpu \
  --dtype bfloat16 \
  --enforce-eager \
  --load-in-low-bit bf16 \
  --max-model-len 4096 \
  --max-num-batched-tokens 10240 \
  --max-num-seqs 12 \
  --tensor-parallel-size 1

[leoneyar]

Hi @leoneyar,

It seems that the none setting for load-in-low-bit in your scripts is invalid for this command. I suggest trying the settings we provide:

python -m ipex_llm.vllm.cpu.entrypoints.openai.api_server
--served-model-name $served_model_name
--port 8000
--model $model
--trust-remote-code
--device cpu
--dtype bfloat16
--enforce-eager
--load-in-low-bit bf16
--max-model-len 4096
--max-num-batched-tokens 10240
--max-num-seqs 12
--tensor-parallel-size 1

Hi @xiangyuT ，I changed it and it's still the same error

[xiangyuT]

Hi @xiangyuT ，I changed it and it's still the same error

The CPU (E7-4830 v2) does not support the AVX512 or even the AVX 2 Instruction Set Architecture. You may need to test this in a more modern environment.

If you are using our docker image (intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT), you might want to recompile the vLLM CPU in your current environment since the version in the docker image is built with AVX512 ISA flag.

pip uninstall vllm
cd /vllm
VLLM_TARGET_DEVICE=cpu python3 setup.py install