llama.cpp for SYCL

Background
Recommended Release
News
OS
Hardware
Docker
Linux
Windows
Environment Variable
Known Issue
Q&A
TODO

Background

SYCL is a high-level parallel programming model designed to improve developers productivity writing code across various hardware accelerators such as CPUs, GPUs, and FPGAs. It is a single-source language designed for heterogeneous computing and based on standard C++17.

oneAPI is an open ecosystem and a standard-based specification, supporting multiple architectures including but not limited to intel CPUs, GPUs and FPGAs. The key components of the oneAPI ecosystem include:

DPCPP (Data Parallel C++): The primary oneAPI SYCL implementation, which includes the icpx/icx Compilers.
oneAPI Libraries: A set of highly optimized libraries targeting multiple domains (e.g. oneMKL - Math Kernel Library).
oneAPI LevelZero: A high performance low level interface for fine-grained control over intel iGPUs and dGPUs.
Nvidia & AMD Plugins: These are plugins extending oneAPI's DPCPP support to SYCL on Nvidia and AMD GPU targets.

Llama.cpp + SYCL

The llama.cpp SYCL backend is designed to support Intel GPU firstly. Based on the cross-platform feature of SYCL, it could support other vendor GPUs: Nvidia GPU (AMD GPU coming).

When targeting Intel CPU, it is recommended to use llama.cpp for Intel oneMKL backend.

It has the similar design of other llama.cpp BLAS-based paths such as OpenBLAS, cuBLAS, etc... In beginning work, the oneAPI's SYCLomatic open-source migration tool (Commercial release Intel® DPC++ Compatibility Tool) was used for this purpose.

Recommended Release

The SYCL backend would be broken by some PRs due to no online CI.

The following release is verified with good quality:

Commit ID	Tag	Release	Verified Platform
fb76ec31a9914b7761c1727303ab30380fd4f05c	b3038	llama-b3038-bin-win-sycl-x64.zip	Arc770/Linux/oneAPI 2024.1 MTL Arc GPU/Windows 11/oneAPI 2024.1

News

2024.5
- Performance is increased: 34 -> 37 tokens/s of llama-2-7b.Q4_0 on Arc770.
- Arch Linux is verified successfully.
2024.4
- Support data types: GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M.
2024.3
- Release binary files of Windows.
- A blog is published: Run LLM on all Intel GPUs Using llama.cpp: intel.com or medium.com.
- New base line is ready: tag b2437.
- Support multiple cards: --split-mode: [none|layer]; not support [row], it's on developing.
- Support to assign main GPU by --main-gpu, replace $GGML_SYCL_DEVICE.
- Support detecting all GPUs with level-zero and same top Max compute units.
- Support OPs
  - hardsigmoid
  - hardswish
  - pool2d
2024.1
- Create SYCL backend for Intel GPU.
- Support Windows build

OS

OS	Status	Verified
Linux	Support	Ubuntu 22.04, Fedora Silverblue 39, Arch Linux
Windows	Support	Windows 11

Hardware

Intel GPU

SYCL backend supports Intel GPU Family:

Intel Data Center Max Series
Intel Flex Series, Arc Series
Intel Built-in Arc GPU
Intel iGPU in Core CPU (11th Generation Core CPU and newer, refer to oneAPI supported GPU).

Verified devices

Intel GPU	Status	Verified Model
Intel Data Center Max Series	Support	Max 1550, 1100
Intel Data Center Flex Series	Support	Flex 170
Intel Arc Series	Support	Arc 770, 730M, Arc A750
Intel built-in Arc GPU	Support	built-in Arc GPU in Meteor Lake
Intel iGPU	Support	iGPU in 13700k, i5-1250P, i7-1260P, i7-1165G7

Notes:

Memory
- The device memory is a limitation when running a large model. The loaded model size, llm_load_tensors: buffer_size, is displayed in the log when running ./bin/llama-cli.
- Please make sure the GPU shared memory from the host is large enough to account for the model's size. For e.g. the llama-2-7b.Q4_0 requires at least 8.0GB for integrated GPU and 4.0GB for discrete GPU.
Execution Unit (EU)
- If the iGPU has less than 80 EUs, the inference speed will likely be too slow for practical use.

Other Vendor GPU

Verified devices

Nvidia GPU	Status	Verified Model
Ampere Series	Support	A100, A4000
Ampere Series (Mobile)	Support	RTX 40 Series

Docker

The docker build option is currently limited to intel GPU targets.

Build image

# Using FP16
docker build -t llama-cpp-sycl --build-arg="GGML_SYCL_F16=ON" -f .devops/llama-cli-intel.Dockerfile .

Notes:

To build in default FP32 (Slower than FP16 alternative), you can remove the --build-arg="GGML_SYCL_F16=ON" argument from the previous command.

You can also use the .devops/llama-server-intel.Dockerfile, which builds the "server" alternative.

Run container

# First, find all the DRI cards
ls -la /dev/dri
# Then, pick the card that you want to use (here for e.g. /dev/dri/card1).
docker run -it --rm -v "$(pwd):/app:Z" --device /dev/dri/renderD128:/dev/dri/renderD128 --device /dev/dri/card1:/dev/dri/card1 llama-cpp-sycl -m "/app/models/YOUR_MODEL_FILE" -p "Building a website can be done in 10 simple steps:" -n 400 -e -ngl 33

Notes:

Docker has been tested successfully on native Linux. WSL support has not been verified yet.
You may need to install Intel GPU driver on the host machine (Please refer to the Linux configuration for details).

Linux

I. Setup Environment

Install GPU drivers

Intel GPU

Intel data center GPUs drivers installation guide and download page can be found here: Get intel dGPU Drivers.

Note: for client GPUs (iGPU & Arc A-Series), please refer to the client iGPU driver installation.

Once installed, add the user(s) to the video and render groups.

sudo usermod -aG render $USER
sudo usermod -aG video $USER

Note: logout/re-login for the changes to take effect.

Verify installation through clinfo:

sudo apt install clinfo
sudo clinfo -l

Sample output:

Platform #0: Intel(R) OpenCL Graphics
 `-- Device #0: Intel(R) Arc(TM) A770 Graphics

Platform #0: Intel(R) OpenCL HD Graphics
 `-- Device #0: Intel(R) Iris(R) Xe Graphics [0x9a49]

Nvidia GPU

In order to target Nvidia GPUs through SYCL, please make sure the CUDA/CUBLAS native requirements -found here- are installed.

Install Intel® oneAPI Base toolkit

For Intel GPU

The base toolkit can be obtained from the official Intel® oneAPI Base Toolkit page.

Please follow the instructions for downloading and installing the Toolkit for Linux, and preferably keep the default installation values unchanged, notably the installation path (/opt/intel/oneapi by default).

Following guidelines/code snippets assume the default installation values. Otherwise, please make sure the necessary changes are reflected where applicable.

Upon a successful installation, SYCL is enabled for the available intel devices, along with relevant libraries such as oneAPI MKL for intel GPUs.

Adding support to Nvidia GPUs

oneAPI Plugin: In order to enable SYCL support on Nvidia GPUs, please install the Codeplay oneAPI Plugin for Nvidia GPUs. User should also make sure the plugin version matches the installed base toolkit one (previous step) for a seamless "oneAPI on Nvidia GPU" setup.

oneMKL for cuBlas: The current oneMKL releases (shipped with the oneAPI base-toolkit) do not contain the cuBLAS backend. A build from source of the upstream oneMKL with the cuBLAS backend enabled is thus required to run it on Nvidia GPUs.

git clone https://github.com/oneapi-src/oneMKL
cd oneMKL
cmake -B buildWithCublas -DCMAKE_CXX_COMPILER=icpx -DCMAKE_C_COMPILER=icx -DENABLE_MKLGPU_BACKEND=OFF -DENABLE_MKLCPU_BACKEND=OFF -DENABLE_CUBLAS_BACKEND=ON -DTARGET_DOMAINS=blas
cmake --build buildWithCublas --config Release

Verify installation and environment

In order to check the available SYCL devices on the machine, please use the sycl-ls command.

source /opt/intel/oneapi/setvars.sh
sycl-ls

Intel GPU

When targeting an intel GPU, the user should expect one or more level-zero devices among the available SYCL devices. Please make sure that at least one GPU is present, for instance [ext_oneapi_level_zero:gpu:0] in the sample output below:

[opencl:acc:0] Intel(R) FPGA Emulation Platform for OpenCL(TM), Intel(R) FPGA Emulation Device OpenCL 1.2  [2023.16.10.0.17_160000]
[opencl:cpu:1] Intel(R) OpenCL, 13th Gen Intel(R) Core(TM) i7-13700K OpenCL 3.0 (Build 0) [2023.16.10.0.17_160000]
[opencl:gpu:2] Intel(R) OpenCL Graphics, Intel(R) Arc(TM) A770 Graphics OpenCL 3.0 NEO  [23.30.26918.50]
[ext_oneapi_level_zero:gpu:0] Intel(R) Level-Zero, Intel(R) Arc(TM) A770 Graphics 1.3 [1.3.26918]

Nvidia GPU

Similarly, user targeting Nvidia GPUs should expect at least one SYCL-CUDA device [ext_oneapi_cuda:gpu] as bellow:

[opencl:acc:0] Intel(R) FPGA Emulation Platform for OpenCL(TM), Intel(R) FPGA Emulation Device OpenCL 1.2  [2023.16.12.0.12_195853.xmain-hotfix]
[opencl:cpu:1] Intel(R) OpenCL, Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz OpenCL 3.0 (Build 0) [2023.16.12.0.12_195853.xmain-hotfix]
[ext_oneapi_cuda:gpu:0] NVIDIA CUDA BACKEND, NVIDIA A100-PCIE-40GB 8.0 [CUDA 12.2]

II. Build llama.cpp

Intel GPU

./examples/sycl/build.sh

or

# Export relevant ENV variables
source /opt/intel/oneapi/setvars.sh

# Build LLAMA with MKL BLAS acceleration for intel GPU

# Option 1: Use FP32 (recommended for better performance in most cases)
cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx

# Option 2: Use FP16
cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON

# build all binary
cmake --build build --config Release -j -v

Nvidia GPU

# Export relevant ENV variables
export LD_LIBRARY_PATH=/path/to/oneMKL/buildWithCublas/lib:$LD_LIBRARY_PATH
export LIBRARY_PATH=/path/to/oneMKL/buildWithCublas/lib:$LIBRARY_PATH
export CPLUS_INCLUDE_DIR=/path/to/oneMKL/buildWithCublas/include:$CPLUS_INCLUDE_DIR
export CPLUS_INCLUDE_DIR=/path/to/oneMKL/include:$CPLUS_INCLUDE_DIR

# Build LLAMA with Nvidia BLAS acceleration through SYCL

# Option 1: Use FP32 (recommended for better performance in most cases)
cmake -B build -DGGML_SYCL=ON -DGGML_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx

# Option 2: Use FP16
cmake -B build -DGGML_SYCL=ON -DGGML_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON

# build all binary
cmake --build build --config Release -j -v

III. Run the inference

Retrieve and prepare model

You can refer to the general Prepare and Quantize guide for model prepration, or simply download llama-2-7b.Q4_0.gguf model as example.

Check device

Enable oneAPI running environment

source /opt/intel/oneapi/setvars.sh

List devices information

Similar to the native sycl-ls, available SYCL devices can be queried as follow:

./build/bin/llama-ls-sycl-device

This command will only display the selected backend that is supported by SYCL. The default backend is level_zero. For example, in a system with 2 intel GPU it would look like the following:

found 2 SYCL devices:

|  |                  |                                             |Compute   |Max compute|Max work|Max sub|               |
|ID|       Device Type|                                         Name|capability|units      |group   |group  |Global mem size|
|--|------------------|---------------------------------------------|----------|-----------|--------|-------|---------------|
| 0|[level_zero:gpu:0]|               Intel(R) Arc(TM) A770 Graphics|       1.3|        512|    1024|     32|    16225243136|
| 1|[level_zero:gpu:1]|                    Intel(R) UHD Graphics 770|       1.3|         32|     512|     32|    53651849216|

Choose level-zero devices

Chosen Device ID	Setting
0	`export ONEAPI_DEVICE_SELECTOR="level_zero:1"` or no action
1	`export ONEAPI_DEVICE_SELECTOR="level_zero:1"`
0 & 1	`export ONEAPI_DEVICE_SELECTOR="level_zero:0;level_zero:1"`

Execute

Choose one of following methods to run.

Script

Use device 0:

./examples/sycl/run_llama2.sh 0

Use multiple devices:

./examples/sycl/run_llama2.sh

Command line Launch inference

There are two device selection modes:

Single device: Use one device assigned by user. Default device id is 0.
Multiple devices: Automatically choose the devices with the same backend.

In two device selection modes, the default SYCL backend is level_zero, you can choose other backend supported by SYCL by setting environment variable ONEAPI_DEVICE_SELECTOR.

Device selection	Parameter
Single device	--split-mode none --main-gpu DEVICE_ID
Multiple devices	--split-mode layer (default)

Examples:

Use device 0:

ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "Building a website can be done in 10 simple steps:" -n 400 -e -ngl 33 -sm none -mg 0

Use multiple devices:

ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "Building a website can be done in 10 simple steps:" -n 400 -e -ngl 33 -sm layer

Notes:

Upon execution, verify the selected device(s) ID(s) in the output log, which can for instance be displayed as follow:

detect 1 SYCL GPUs: [0] with top Max compute units:512

Or

use 1 SYCL GPUs: [0] with Max compute units:512

Windows

I. Setup Environment

Install GPU driver

Intel GPU drivers instructions guide and download page can be found here: Get intel GPU Drivers.

Install Visual Studio

If you already have a recent version of Microsoft Visual Studio, you can skip this step. Otherwise, please refer to the official download page for Microsoft Visual Studio.

Install Intel® oneAPI Base toolkit

The base toolkit can be obtained from the official Intel® oneAPI Base Toolkit page.

Please follow the instructions for downloading and installing the Toolkit for Windows, and preferably keep the default installation values unchanged, notably the installation path (C:\Program Files (x86)\Intel\oneAPI by default).

Following guidelines/code snippets assume the default installation values. Otherwise, please make sure the necessary changes are reflected where applicable.

b. Enable oneAPI running environment:

Type "oneAPI" in the search bar, then open the Intel oneAPI command prompt for Intel 64 for Visual Studio 2022 App.
On the command prompt, enable the runtime environment with the following:

"C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64

c. Verify installation

In the oneAPI command line, run the following to print the available SYCL devices:

sycl-ls.exe

There should be one or more level-zero GPU devices displayed as [ext_oneapi_level_zero:gpu]. Below is example of such output detecting an intel Iris Xe GPU as a Level-zero SYCL device:

Output (example):

[opencl:acc:0] Intel(R) FPGA Emulation Platform for OpenCL(TM), Intel(R) FPGA Emulation Device OpenCL 1.2  [2023.16.10.0.17_160000]
[opencl:cpu:1] Intel(R) OpenCL, 11th Gen Intel(R) Core(TM) i7-1185G7 @ 3.00GHz OpenCL 3.0 (Build 0) [2023.16.10.0.17_160000]
[opencl:gpu:2] Intel(R) OpenCL Graphics, Intel(R) Iris(R) Xe Graphics OpenCL 3.0 NEO  [31.0.101.5186]
[ext_oneapi_level_zero:gpu:0] Intel(R) Level-Zero, Intel(R) Iris(R) Xe Graphics 1.3 [1.3.28044]

Install build tools

a. Download & install cmake for Windows: https://cmake.org/download/ (CMake can also be installed from Visual Studio Installer) b. The new Visual Studio will install Ninja as default. (If not, please install it manually: https://ninja-build.org/)

II. Build llama.cpp

You could download the release package for Windows directly, which including binary files and depended oneAPI dll files.

Choose one of following methods to build from source code.

Script

.\examples\sycl\win-build-sycl.bat

CMake

On the oneAPI command line window, step into the llama.cpp main directory and run the following:

@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force

# Option 1: Use FP32 (recommended for better performance in most cases)
cmake -B build -G "Ninja" -DGGML_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx  -DCMAKE_BUILD_TYPE=Release

# Option 2: Or FP16
cmake -B build -G "Ninja" -DGGML_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx  -DCMAKE_BUILD_TYPE=Release -DGGML_SYCL_F16=ON

cmake --build build --config Release -j

Or, use CMake presets to build:

cmake --preset x64-windows-sycl-release
cmake --build build-x64-windows-sycl-release -j --target llama-cli

cmake -DGGML_SYCL_F16=ON --preset x64-windows-sycl-release
cmake --build build-x64-windows-sycl-release -j --target llama-cli

cmake --preset x64-windows-sycl-debug
cmake --build build-x64-windows-sycl-debug -j --target llama-cli

Visual Studio

You can use Visual Studio to open llama.cpp folder as a CMake project. Choose the sycl CMake presets (x64-windows-sycl-release or x64-windows-sycl-debug) before you compile the project.

Notes:

In case of a minimal experimental setup, the user can build the inference executable only through cmake --build build --config Release -j --target llama-cli.

III. Run the inference

Retrieve and prepare model

You can refer to the general Prepare and Quantize guide for model prepration, or simply download llama-2-7b.Q4_0.gguf model as example.

Check device

Enable oneAPI running environment

On the oneAPI command line window, run the following and step into the llama.cpp directory:

"C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64

List devices information

Similar to the native sycl-ls, available SYCL devices can be queried as follow:

build\bin\llama-ls-sycl-device.exe

This command will only display the selected backend that is supported by SYCL. The default backend is level_zero. For example, in a system with 2 intel GPU it would look like the following:

found 2 SYCL devices:
|  |                  |                                             |Compute   |Max compute|Max work|Max sub|               |
|ID|       Device Type|                                         Name|capability|units      |group   |group  |Global mem size|
|--|------------------|---------------------------------------------|----------|-----------|--------|-------|---------------|
| 0|[level_zero:gpu:0]|               Intel(R) Arc(TM) A770 Graphics|       1.3|        512|    1024|     32|    16225243136|
| 1|[level_zero:gpu:1]|                    Intel(R) UHD Graphics 770|       1.3|         32|     512|     32|    53651849216|

Choose level-zero devices

Chosen Device ID	Setting
0	`set ONEAPI_DEVICE_SELECTOR="level_zero:1"` or no action
1	`set ONEAPI_DEVICE_SELECTOR="level_zero:1"`
0 & 1	`set ONEAPI_DEVICE_SELECTOR="level_zero:0;level_zero:1"`

Execute

Choose one of following methods to run.

Script

examples\sycl\win-run-llama2.bat

Command line

Launch inference

There are two device selection modes:

Single device: Use one device assigned by user. Default device id is 0.
Multiple devices: Automatically choose the devices with the same backend.

In two device selection modes, the default SYCL backend is level_zero, you can choose other backend supported by SYCL by setting environment variable ONEAPI_DEVICE_SELECTOR.

Device selection	Parameter
Single device	--split-mode none --main-gpu DEVICE_ID
Multiple devices	--split-mode layer (default)

Examples:

Use device 0:

build\bin\llama-cli.exe -m models\llama-2-7b.Q4_0.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e -ngl 33 -s 0 -sm none -mg 0

Use multiple devices:

build\bin\llama-cli.exe -m models\llama-2-7b.Q4_0.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e -ngl 33 -s 0 -sm layer

Note:

Upon execution, verify the selected device(s) ID(s) in the output log, which can for instance be displayed as follow:

detect 1 SYCL GPUs: [0] with top Max compute units:512

Or

use 1 SYCL GPUs: [0] with Max compute units:512

Environment Variable

Build

Name	Value	Function
GGML_SYCL	ON (mandatory)	Enable build with SYCL code path. FP32 path - recommended for better perforemance than FP16 on quantized model
GGML_SYCL_TARGET	INTEL (default) \| NVIDIA	Set the SYCL target device type.
GGML_SYCL_F16	OFF (default) \|ON (optional)	Enable FP16 build with SYCL code path.
CMAKE_C_COMPILER	`icx` (Linux), `icx/cl` (Windows)	Set `icx` compiler for SYCL code path.
CMAKE_CXX_COMPILER	`icpx` (Linux), `icx` (Windows)	Set `icpx/icx` compiler for SYCL code path.

Runtime

Name	Value	Function
GGML_SYCL_DEBUG	0 (default) or 1	Enable log function by macro: GGML_SYCL_DEBUG
ZES_ENABLE_SYSMAN	0 (default) or 1	Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory. Recommended to use when --split-mode = layer

Known Issues

Split-mode:[row] is not supported.

Q&A

Error: error while loading shared libraries: libsycl.so.7: cannot open shared object file: No such file or directory.
- Potential cause: Unavailable oneAPI installation or not set ENV variables.
- Solution: Install oneAPI base toolkit and enable its ENV through: source /opt/intel/oneapi/setvars.sh.
General compiler error:
- Remove build folder or try a clean-build.
I can not see [ext_oneapi_level_zero:gpu] afer installing the GPU driver on Linux.

Please double-check with sudo sycl-ls.

If it's present in the list, please add video/render group to your user then logout/login or restart your system:
```
sudo usermod -aG render $USER
sudo usermod -aG video $USER
```
Otherwise, please double-check the GPU driver installation steps.
Can I report Ollama issue on Intel GPU to llama.cpp SYCL backend?

No. We can't support Ollama issue directly, because we aren't familiar with Ollama.

Sugguest reproducing on llama.cpp and report similar issue to llama.cpp. We will surpport it.

It's same for other projects including llama.cpp SYCL backend.

GitHub contribution:

Please add the [SYCL] prefix/tag in issues/PRs titles to help the SYCL-team check/address them without delay.

TODO

NA

Files

SYCL.md

Latest commit

History

SYCL.md

File metadata and controls

llama.cpp for SYCL

Background

Llama.cpp + SYCL

Recommended Release

News

OS

Hardware

Intel GPU

Verified devices

Other Vendor GPU

Docker

Build image

Run container

Linux

I. Setup Environment

II. Build llama.cpp

Intel GPU

Nvidia GPU

III. Run the inference

Retrieve and prepare model

Check device

Choose level-zero devices

Execute

Windows

I. Setup Environment

II. Build llama.cpp

III. Run the inference

Retrieve and prepare model

Check device

Choose level-zero devices

Execute

Environment Variable

Build

Runtime

Known Issues

Q&A

GitHub contribution:

TODO