Use model cache for docker compose test (#1582)

Signed-off-by: ZePan110 <ze.pan@intel.com>
This commit is contained in:
ZePan110
2025-03-04 09:48:27 +08:00
committed by GitHub
parent ce38a84372
commit e4de76da78
28 changed files with 61 additions and 31 deletions

View File

@@ -21,7 +21,7 @@ services:
timeout: 10s
retries: 100
volumes:
- "./data:/data"
- "${MODEL_CACHE}:/data"
shm_size: 1g
command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
llm:

View File

@@ -30,7 +30,7 @@ services:
- SYS_NICE
ipc: host
volumes:
- "./data:/data"
- "${MODEL_CACHE}:/data"
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
llm:
image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}