thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566)

Browse source 
Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>
This commit is contained in:
Neo Zhang 2025-11-29 20:59:44 +08:00 • committed by GitHub
parent f698a79c63
commit 7d2add51d8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 33 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/sycl/run-llama2.sh
View file

@ -15,6 +15,9 @@ MODEL_FILE=models/llama-2-7b.Q4_0.gguf
NGL=99
CONTEXT=4096
#support malloc device memory more than 4GB.
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
if [ $# -gt 0 ]; then
GGML_SYCL_DEVICE=$1
echo "use $GGML_SYCL_DEVICE as main GPU"

9
examples/sycl/run-llama3.sh
View file

@ -6,7 +6,7 @@
# If you want more control, DPC++ Allows selecting a specific device through the
# following environment variable
#export ONEAPI_DEVICE_SELECTOR="level_zero:0"
export ONEAPI_DEVICE_SELECTOR="level_zero:0"
source /opt/intel/oneapi/setvars.sh
#export GGML_SYCL_DEBUG=1
@ -18,11 +18,14 @@ MODEL_FILE=models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
NGL=99 # Layers offloaded to the GPU. If the device runs out of memory, reduce this value according to the model you are using.
CONTEXT=4096
#support malloc device memory more than 4GB.
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
if [ $# -gt 0 ]; then
GGML_SYCL_DEVICE=$1
echo "Using $GGML_SYCL_DEVICE as the main GPU"
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -c ${CONTEXT} -mg $GGML_SYCL_DEVICE -sm none
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT} -mg $GGML_SYCL_DEVICE -sm none
else
#use multiple GPUs with same max compute units
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -c ${CONTEXT}
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT}
fi

2
examples/sycl/win-run-llama2.bat
View file

@ -5,5 +5,7 @@
set INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
:: support malloc device memory more than 4GB.
set UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
.\build\bin\llama-cli.exe -m models\llama-2-7b.Q4_0.gguf -p %INPUT2% -n 400 -e -ngl 99 -s 0

4
examples/sycl/win-run-llama3.bat
View file

@ -5,5 +5,7 @@
set INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
:: support malloc device memory more than 4GB.
set UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
.\build\bin\llama-cli.exe -m models\Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -p %INPUT2% -n 400 -e -ngl 99
.\build\bin\llama-cli.exe -m models\Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -p %INPUT2% -n 400 -s 0 -e -ngl 99