char-fork/llama.cpp

git clone https://git.t4t.associates/char-fork/llama.cpp

Charlotte Somenc/dec in server context8300f1411

char/aliceai-t5-moe
brancheschar/aliceai-t5-moeall refs →
13 files

files

CMakeLists.txt341 B
README.md1.4 KiB
build.sh1.3 KiB
ls-sycl-device.cpp251 B
run-llama2.sh1.1 KiB
start-svr.sh4.0 KiB
test.sh4.4 KiB
update-ops-doc.sh210 B
win-build-sycl.bat1.4 KiB
win-run-llama2.bat481 B
win-start-svr.bat4.7 KiB
win-test.bat5.2 KiB
win-update-ops-doc.bat204 B

llama.cpp/example/sycl

This example program provides the tools for llama.cpp for SYCL on Intel GPU.

Tool

Tool NameFunctionStatus
llama-ls-sycl-deviceList all SYCL devices with ID, compute capability, max work group size, etc.Support

llama-ls-sycl-device

List all SYCL devices with ID, compute capability, max work group size, etc.

  1. Build the llama.cpp for SYCL for the specified target (using GGML_SYCL_TARGET).

  2. Enable oneAPI running environment (if GGML_SYCL_TARGET is set to INTEL -default-)

source /opt/intel/oneapi/setvars.sh
  1. Execute
./build/bin/llama-ls-sycl-device

Check the ID in startup log, like:

found 2 SYCL devices:
|  |                   |                                       |       |Max    |        |Max  |Global |                     |
|  |                   |                                       |       |compute|Max work|sub  |mem    |                     |
|ID|        Device Type|                                   Name|Version|units  |group   |group|size   |       Driver version|
|--|-------------------|---------------------------------------|-------|-------|--------|-----|-------|---------------------|
| 0| [level_zero:gpu:0]|                Intel Arc A770 Graphics|    1.3|    512|    1024|   32| 16225M|            1.3.29138|
| 1| [level_zero:gpu:1]|                 Intel UHD Graphics 750|    1.3|     32|     512|   32| 62631M|            1.3.29138|