CPU¶

vLLM is a Python library that supports the following CPU variants. Select your CPU type to see vendor specific instructions:

Requirements¶

• Python: 3.9 -- 3.12

Set up using Python¶

Create a new Python environment¶

It's recommended to use uv, a very fast Python environment manager, to create and manage Python environments. Please follow the documentation to install uv. After installing uv, you can create a new Python environment and install vLLM using the following commands:

uv venv --python 3.12 --seed
source .venv/bin/activate

Pre-built wheels¶

Currently, there are no pre-built CPU wheels.

Build wheel from source¶

sudo apt-get update  -y
sudo apt-get install -y --no-install-recommends ccache git curl wget ca-certificates gcc-12 g++-12 libtcmalloc-minimal4 libnuma-dev ffmpeg libsm6 libxext6 libgl1 jq lsof
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12

git clone https://github.com/vllm-project/vllm.git vllm_source
cd vllm_source

uv pip install -r requirements/cpu-build.txt --torch-backend auto
uv pip install -r requirements/cpu.txt --torch-backend auto

pip install --upgrade pip
pip install -v -r requirements/cpu-build.txt --extra-index-url https://download.pytorch.org/whl/cpu
pip install -v -r requirements/cpu.txt --extra-index-url https://download.pytorch.org/whl/cpu

VLLM_TARGET_DEVICE=cpu python setup.py install

VLLM_TARGET_DEVICE=cpu python setup.py develop

sudo apt-get update  -y
sudo apt-get install -y --no-install-recommends ccache git curl wget ca-certificates gcc-12 g++-12 libtcmalloc-minimal4 libnuma-dev ffmpeg libsm6 libxext6 libgl1 jq lsof
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12

git clone https://github.com/vllm-project/vllm.git vllm_source
cd vllm_source

uv pip install -r requirements/cpu-build.txt --torch-backend auto
uv pip install -r requirements/cpu.txt --torch-backend auto

pip install --upgrade pip
pip install -v -r requirements/cpu-build.txt --extra-index-url https://download.pytorch.org/whl/cpu
pip install -v -r requirements/cpu.txt --extra-index-url https://download.pytorch.org/whl/cpu

VLLM_TARGET_DEVICE=cpu python setup.py install

VLLM_TARGET_DEVICE=cpu python setup.py develop

git clone https://github.com/vllm-project/vllm.git
cd vllm
uv pip install -r requirements/cpu.txt
uv pip install -e .

[...] fatal error: 'map' file not found
        1 | #include <map>
            |          ^~~~~
    1 error generated.
    [2/8] Building CXX object CMakeFiles/_C.dir/csrc/cpu/pos_encoding.cpp.o

[...] fatal error: 'cstddef' file not found
        10 | #include <cstddef>
            |          ^~~~~~~~~
    1 error generated.

dnf install -y \
    which procps findutils tar vim git gcc g++ make patch make cython zlib-devel \
    libjpeg-turbo-devel libtiff-devel libpng-devel libwebp-devel freetype-devel harfbuzz-devel \
    openssl-devel openblas openblas-devel wget autoconf automake libtool cmake numactl-devel

curl https://sh.rustup.rs -sSf | sh -s -- -y && \
    . "$HOME/.cargo/env"

    sed -i '/^torch/d' requirements-build.txt    # remove torch from requirements-build.txt since we use nightly builds
    uv pip install -v \
        --torch-backend auto \
        -r requirements-build.txt \
        -r requirements-cpu.txt \
    VLLM_TARGET_DEVICE=cpu python setup.py bdist_wheel && \
        uv pip install dist/*.whl

    sed -i '/^torch/d' requirements-build.txt    # remove torch from requirements-build.txt since we use nightly builds
    pip install -v \
        --extra-index-url https://download.pytorch.org/whl/nightly/cpu \
        -r requirements-build.txt \
        -r requirements-cpu.txt \
    VLLM_TARGET_DEVICE=cpu python setup.py bdist_wheel && \
        pip install dist/*.whl

Set up using Docker¶

Pre-built images¶

Build image from source¶

docker build -f docker/Dockerfile.cpu \
        --build-arg VLLM_CPU_AVX512BF16=false (default)|true \
        --build-arg VLLM_CPU_AVX512VNNI=false (default)|true \
        --build-arg VLLM_CPU_DISABLE_AVX512=false (default)|true \ 
        --tag vllm-cpu-env \
        --target vllm-openai .

# Launching OpenAI server
docker run --rm \
            --privileged=true \
            --shm-size=4g \
            -p 8000:8000 \
            -e VLLM_CPU_KVCACHE_SPACE=<KV cache space> \
            -e VLLM_CPU_OMP_THREADS_BIND=<CPU cores for inference> \
            vllm-cpu-env \
            --model=meta-llama/Llama-3.2-1B-Instruct \
            --dtype=bfloat16 \
            other vLLM OpenAI server arguments

docker build -f docker/Dockerfile.cpu \
        --tag vllm-cpu-env .

# Launching OpenAI server
docker run --rm \
            --privileged=true \
            --shm-size=4g \
            -p 8000:8000 \
            -e VLLM_CPU_KVCACHE_SPACE=<KV cache space> \
            -e VLLM_CPU_OMP_THREADS_BIND=<CPU cores for inference> \
            vllm-cpu-env \
            --model=meta-llama/Llama-3.2-1B-Instruct \
            --dtype=bfloat16 \
            other vLLM OpenAI server arguments

docker build -f docker/Dockerfile.cpu \
        --tag vllm-cpu-env .

# Launching OpenAI server
docker run --rm \
            --privileged=true \
            --shm-size=4g \
            -p 8000:8000 \
            -e VLLM_CPU_KVCACHE_SPACE=<KV cache space> \
            -e VLLM_CPU_OMP_THREADS_BIND=<CPU cores for inference> \
            vllm-cpu-env \
            --model=meta-llama/Llama-3.2-1B-Instruct \
            --dtype=bfloat16 \
            other vLLM OpenAI server arguments

docker build -f docker/Dockerfile.s390x \
    --tag vllm-cpu-env .

# Launch OpenAI server
docker run --rm \
    --privileged true \
    --shm-size 4g \
    -p 8000:8000 \
    -e VLLM_CPU_KVCACHE_SPACE=<KV cache space> \
    -e VLLM_CPU_OMP_THREADS_BIND=<CPU cores for inference> \
    vllm-cpu-env \
    --model meta-llama/Llama-3.2-1B-Instruct \
    --dtype float \
    other vLLM OpenAI server arguments

Related runtime environment variables¶

• VLLM_CPU_KVCACHE_SPACE: specify the KV Cache size (e.g, VLLM_CPU_KVCACHE_SPACE=40 means 40 GiB space for KV cache), larger setting will allow vLLM running more requests in parallel. This parameter should be set based on the hardware configuration and memory management pattern of users. Default value is 0.
• VLLM_CPU_OMP_THREADS_BIND: specify the CPU cores dedicated to the OpenMP threads, can be set as CPU id lists or auto (by default). For example, VLLM_CPU_OMP_THREADS_BIND=0-31 means there will be 32 OpenMP threads bound on 0-31 CPU cores. VLLM_CPU_OMP_THREADS_BIND=0-31|32-63 means there will be 2 tensor parallel processes, 32 OpenMP threads of rank0 are bound on 0-31 CPU cores, and the OpenMP threads of rank1 are bound on 32-63 CPU cores. By setting to auto, the OpenMP threads of each rank are bound to the CPU cores in each NUMA node respectively.
• VLLM_CPU_NUM_OF_RESERVED_CPU: specify the number of CPU cores which are not dedicated to the OpenMP threads for each rank. The variable only takes effect when VLLM_CPU_OMP_THREADS_BIND is set to auto. Default value is None. If the value is not set and use auto thread binding, no CPU will be reserved for world_size == 1, 1 CPU per rank will be reserved for world_size > 1.
• VLLM_CPU_MOE_PREPACK (x86 only): whether to use prepack for MoE layer. This will be passed to ipex.llm.modules.GatedMLPMOE. Default is 1 (True). On unsupported CPUs, you might need to set this to 0 (False).
• VLLM_CPU_SGL_KERNEL (x86 only, Experimental): whether to use small-batch optimized kernels for linear layer and MoE layer, especially for low-latency requirements like online serving. The kernels require AMX instruction set, BFloat16 weight type and weight shapes divisible by 32. Default is 0 (False).

FAQ¶

Which dtype should be used?¶

• Currently vLLM CPU uses model default settings as dtype. However, due to unstable float16 support in torch CPU, it is recommended to explicitly set dtype=bfloat16 if there are any performance or accuracy problem.

How to launch a vLLM service on CPU?¶

• When using the online serving, it is recommended to reserve 1-2 CPU cores for the serving framework to avoid CPU oversubscription. For example, on a platform with 32 physical CPU cores, reserving CPU 31 for the framework and using CPU 0-30 for inference threads:

export VLLM_CPU_KVCACHE_SPACE=40
export VLLM_CPU_OMP_THREADS_BIND=0-30
vllm serve facebook/opt-125m --dtype=bfloat16

or using default auto thread binding:

export VLLM_CPU_KVCACHE_SPACE=40
export VLLM_CPU_NUM_OF_RESERVED_CPU=1
vllm serve facebook/opt-125m --dtype=bfloat16

Note, it is recommended to manually reserve 1 CPU for vLLM front-end process when world_size == 1.

How to decide VLLM_CPU_OMP_THREADS_BIND?¶

• Default auto thread-binding is recommended for most cases. Ideally, each OpenMP thread will be bound to a dedicated physical core respectively, threads of each rank will be bound to a same NUMA node respectively, and 1 CPU per rank will be reserved for other vLLM components when world_size > 1. If have any performance problems or unexpected binding behaviours, please try to bind threads as following.

• On a hyper-threading enabled platform with 16 logical CPU cores / 8 physical CPU cores:

$ lscpu -e # check the mapping between logical CPU cores and physical CPU cores

# The "CPU" column means the logical CPU core IDs, and the "CORE" column means the physical core IDs. On this platform, two logical cores are sharing one physical core.
CPU NODE SOCKET CORE L1d:L1i:L2:L3 ONLINE    MAXMHZ   MINMHZ      MHZ
0    0      0    0 0:0:0:0          yes 2401.0000 800.0000  800.000
1    0      0    1 1:1:1:0          yes 2401.0000 800.0000  800.000
2    0      0    2 2:2:2:0          yes 2401.0000 800.0000  800.000
3    0      0    3 3:3:3:0          yes 2401.0000 800.0000  800.000
4    0      0    4 4:4:4:0          yes 2401.0000 800.0000  800.000
5    0      0    5 5:5:5:0          yes 2401.0000 800.0000  800.000
6    0      0    6 6:6:6:0          yes 2401.0000 800.0000  800.000
7    0      0    7 7:7:7:0          yes 2401.0000 800.0000  800.000
8    0      0    0 0:0:0:0          yes 2401.0000 800.0000  800.000
9    0      0    1 1:1:1:0          yes 2401.0000 800.0000  800.000
10   0      0    2 2:2:2:0          yes 2401.0000 800.0000  800.000
11   0      0    3 3:3:3:0          yes 2401.0000 800.0000  800.000
12   0      0    4 4:4:4:0          yes 2401.0000 800.0000  800.000
13   0      0    5 5:5:5:0          yes 2401.0000 800.0000  800.000
14   0      0    6 6:6:6:0          yes 2401.0000 800.0000  800.000
15   0      0    7 7:7:7:0          yes 2401.0000 800.0000  800.000

# On this platform, it is recommend to only bind openMP threads on logical CPU cores 0-7 or 8-15
$ export VLLM_CPU_OMP_THREADS_BIND=0-7
$ python examples/offline_inference/basic/basic.py

• When deploy vLLM CPU backend on a multi-socket machine with NUMA and enable tensor parallel or pipeline parallel, each NUMA node is treated as a TP/PP rank. So be aware to set CPU cores of a single rank on a same NUMA node to avoid cross NUMA node memory access.

How to decide VLLM_CPU_KVCACHE_SPACE?¶

This value is 4GB by default. Larger space can support more concurrent requests, longer context length. However, users should take care of memory capacity of each NUMA node. The memory usage of each TP rank is the sum of weight shard size and VLLM_CPU_KVCACHE_SPACE, if it exceeds the capacity of a single NUMA node, the TP worker will be killed with exitcode 9 due to out-of-memory.

How to do performance tuning for vLLM CPU?¶

First of all, please make sure the thread-binding and KV cache space are properly set and take effect. You can check the thread-binding by running a vLLM benchmark and observing CPU cores usage via htop.

Inference batch size is an important parameter for the performance. Larger batch usually provides higher throughput, smaller batch provides lower latency. Tuning max batch size starts from default value to balance throughput and latency is an effective way to improve vLLM CPU performance on specific platforms. There are two important related parameters in vLLM:

• --max-num-batched-tokens, defines the limit of token numbers in a single batch, has more impacts on the first token performance. The default value is set as:
  • Offline Inference: 4096 * world_size
  • Online Serving: 2048 * world_size
• --max-num-seqs, defines the limit of sequence numbers in a single batch, has more impacts on the output token performance.
  • Offline Inference: 256 * world_size
  • Online Serving: 128 * world_size

vLLM CPU supports tensor parallel (TP) and pipeline parallel (PP) to leverage multiple CPU sockets and memory nodes. For more details of tuning TP and PP, please refer to Optimization and Tuning. For vLLM CPU, it is recommend to use TP and PP together if there are enough CPU sockets and memory nodes.

Which quantization configs does vLLM CPU support?¶

• vLLM CPU supports quantizations:
  • AWQ (x86 only)
  • GPTQ (x86 only)
  • compressed-tensor INT8 W8A8 (x86, s390x)

(x86 only) What is the purpose of VLLM_CPU_MOE_PREPACK and VLLM_CPU_SGL_KERNEL?¶

• Both of them require amx CPU flag.
  • VLLM_CPU_MOE_PREPACK can provides better performance for MoE models
  • VLLM_CPU_SGL_KERNEL can provides better performance for MoE models and small-batch scenarios.