Enchance health check in GenAIExample docker-compose (#1410)

Fix service launch issue

1. Update Gaudi TGI image from 2.0.6 to 2.3.1
2. Change the hpu-gaudi TGI health check condition.

Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
This commit is contained in:
xiguiw
2025-01-20 20:13:13 +08:00
committed by GitHub
parent 59722d2bc9
commit 2d5898244c
17 changed files with 65 additions and 24 deletions

View File

@@ -3,7 +3,7 @@
services:
tgi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.0.6
image: ghcr.io/huggingface/tgi-gaudi:2.3.1
container_name: tgi-gaudi-server
ports:
- ${LLM_ENDPOINT_PORT:-8008}:80
@@ -31,10 +31,10 @@ services:
- SYS_NICE
ipc: host
healthcheck:
test: ["CMD-SHELL", "sleep 500 && exit 0"]
interval: 1s
timeout: 505s
retries: 1
test: ["CMD-SHELL", "curl -f http://${host_ip}:${LLM_ENDPOINT_PORT}/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048 --max-batch-total-tokens 65536 --max-batch-prefill-tokens 4096
llm_faqgen:
image: ${REGISTRY:-opea}/llm-faqgen:${TAG:-latest}