jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Rename image names XXX-hpu to XXX-gaudi (#911)

Browse Source 
Signed-off-by: ZePan110 <ze.pan@intel.com>
This commit is contained in:
ZePan110
2024-11-19 22:06:55 +08:00
committed by GitHub
parent 1bfc4306fd
commit f19cf083d1
17 changed files with 30 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/agent/test_agent_langchain_on_intel_hpu.sh
View File

@@ -51,12 +51,12 @@ function build_vllm_docker_images() {
git clone https://github.com/HabanaAI/vllm-fork.git
fi
cd ./vllm-fork
docker build -f Dockerfile.hpu -t opea/vllm-hpu:comps --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
docker build -f Dockerfile.hpu -t opea/vllm-gaudi:comps --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
if [ $? -ne 0 ]; then
echo "opea/vllm-hpu:comps failed"
echo "opea/vllm-gaudi:comps failed"
exit 1
else
echo "opea/vllm-hpu:comps successful"
echo "opea/vllm-gaudi:comps successful"
fi
}
@@ -88,7 +88,7 @@ function start_vllm_service() {
#single card
echo "start vllm gaudi service"
echo "**************model is $model**************"
docker run -d --runtime=habana --rm --name "test-comps-vllm-gaudi-service" -e HABANA_VISIBLE_DEVICES=all -p $vllm_port:80 -v $vllm_volume:/data -e HF_TOKEN=$HF_TOKEN -e HF_HOME=/data -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e VLLM_SKIP_WARMUP=true --cap-add=sys_nice --ipc=host opea/vllm-hpu:comps --model ${model} --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 4096 --max-seq_len-to-capture 8192
docker run -d --runtime=habana --rm --name "test-comps-vllm-gaudi-service" -e HABANA_VISIBLE_DEVICES=all -p $vllm_port:80 -v $vllm_volume:/data -e HF_TOKEN=$HF_TOKEN -e HF_HOME=/data -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e VLLM_SKIP_WARMUP=true --cap-add=sys_nice --ipc=host opea/vllm-gaudi:comps --model ${model} --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 4096 --max-seq_len-to-capture 8192
sleep 5s
echo "Waiting vllm gaudi ready"
n=0
@@ -115,7 +115,7 @@ function start_vllm_auto_tool_choice_service() {
#single card
echo "start vllm gaudi service"
echo "**************auto_tool model is $model**************"
docker run -d --runtime=habana --rm --name "test-comps-vllm-gaudi-service" -e HABANA_VISIBLE_DEVICES=all -p $vllm_port:80 -v $vllm_volume:/data -e HF_TOKEN=$HF_TOKEN -e HF_HOME=/data -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e VLLM_SKIP_WARMUP=true --cap-add=sys_nice --ipc=host opea/vllm-hpu:comps --model ${model} --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 4096 --max-seq_len-to-capture 8192 --enable-auto-tool-choice --tool-call-parser ${model_parser}
docker run -d --runtime=habana --rm --name "test-comps-vllm-gaudi-service" -e HABANA_VISIBLE_DEVICES=all -p $vllm_port:80 -v $vllm_volume:/data -e HF_TOKEN=$HF_TOKEN -e HF_HOME=/data -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e VLLM_SKIP_WARMUP=true --cap-add=sys_nice --ipc=host opea/vllm-gaudi:comps --model ${model} --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 4096 --max-seq_len-to-capture 8192 --enable-auto-tool-choice --tool-call-parser ${model_parser}
sleep 5s
echo "Waiting vllm gaudi ready"
n=0

8
tests/llms/test_llms_text-generation_vllm_langchain_on_intel_hpu.sh
View File

@@ -13,12 +13,12 @@ function build_docker_images() {
git clone https://github.com/HabanaAI/vllm-fork.git
cd vllm-fork/
git checkout 3c39626
docker build --no-cache -f Dockerfile.hpu -t opea/vllm-hpu:comps --shm-size=128g .
docker build --no-cache -f Dockerfile.hpu -t opea/vllm-gaudi:comps --shm-size=128g .
if [ $? -ne 0 ]; then
echo "opea/vllm-hpu built fail"
echo "opea/vllm-gaudi built fail"
exit 1
else
echo "opea/vllm-hpu built successful"
echo "opea/vllm-gaudi built successful"
fi
## Build OPEA microservice docker
@@ -47,7 +47,7 @@ function start_service() {
--cap-add=sys_nice \
--ipc=host \
-e HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN} \
opea/vllm-hpu:comps \
opea/vllm-gaudi:comps \
--enforce-eager --model $LLM_MODEL --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
export vLLM_ENDPOINT="http://${ip_address}:${port_number}"

8
tests/llms/test_llms_text-generation_vllm_llamaindex_on_intel_hpu.sh
View File

@@ -13,12 +13,12 @@ function build_docker_images() {
git clone https://github.com/HabanaAI/vllm-fork.git
cd vllm-fork/
git checkout 3c39626
docker build --no-cache -f Dockerfile.hpu -t opea/vllm-hpu:comps --shm-size=128g .
docker build --no-cache -f Dockerfile.hpu -t opea/vllm-gaudi:comps --shm-size=128g .
if [ $? -ne 0 ]; then
echo "opea/vllm-hpu built fail"
echo "opea/vllm-gaudi built fail"
exit 1
else
echo "opea/vllm-hpu built successful"
echo "opea/vllm-gaudi built successful"
fi
## Build OPEA microservice docker
@@ -47,7 +47,7 @@ function start_service() {
--cap-add=sys_nice \
--ipc=host \
-e HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN} \
opea/vllm-hpu:comps \
opea/vllm-gaudi:comps \
--enforce-eager --model $LLM_MODEL --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
export vLLM_ENDPOINT="http://${ip_address}:${port_number}"