Skip to content

Update CodeGen for GenAIComps Refactor #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lvliang-intel wants to merge 1 commit into
base: genaicomps_refactor
Choose a base branch
from
Open

Update CodeGen for GenAIComps Refactor #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions CodeGen/docker_compose/amd/gpu/rocm/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,12 @@ services:
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:8008/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
shm_size: 1g
devices:
- /dev/kfd:/dev/kfd
Expand All @@ -31,15 +37,17 @@ services:
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: codegen-llm-server
depends_on:
- codegen-tgi-service
codegen-tgi-service:
condition: service_healthy
ports:
- "${CODEGEN_LLM_SERVICE_PORT:-9000}:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: "http://codegen-tgi-service"
LLM_ENDPOINT: "http://codegen-tgi-service"
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
codegen-backend-server:
Expand Down
12 changes: 10 additions & 2 deletions CodeGen/docker_compose/intel/cpu/xeon/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,20 +15,28 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:8008/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
llm:
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-server
depends_on:
- tgi-service
tgi-service:
condition: service_healthy
ports:
- "9000:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
codegen-xeon-backend-server:
Expand Down
11 changes: 9 additions & 2 deletions CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,11 @@ services:
LIMIT_HPU_GRAPH: true
USE_FLASH_ATTENTION: true
FLASH_ATTENTION_RECOMPUTE: true
healthcheck:
test: ["CMD-SHELL", "sleep 500 && exit 0"]
interval: 1s
timeout: 505s
retries: 1
runtime: habana
cap_add:
- SYS_NICE
Expand All @@ -29,15 +34,17 @@ services:
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-gaudi-server
depends_on:
- tgi-service
tgi-service:
condition: service_healthy
ports:
- "9000:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
codegen-gaudi-backend-server:
Expand Down
Loading