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

Update compose.yaml (#1619)

Browse Source 
Update compose.yaml for CodeGen, CodeTrans and DocSum

Signed-off-by: ZePan110 <ze.pan@intel.com>
This commit is contained in:
ZePan110
2025-03-07 09:20:28 +08:00
committed by GitHub
parent 6723395e31
commit 5aecea8e47
5 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CodeGen/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -8,7 +8,7 @@ services:
ports: ports:
- "8028:80" - "8028:80"
volumes: volumes:
- "${MODEL_CACHE}:/data" - "${MODEL_CACHE:-./data}:/data"
shm_size: 1g shm_size: 1g
environment: environment:
no_proxy: ${no_proxy} no_proxy: ${no_proxy}

2
CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -8,7 +8,7 @@ services:
ports: ports:
- "8028:80" - "8028:80"
volumes: volumes:
- "${MODEL_CACHE}:/data" - "${MODEL_CACHE:-./data}:/data"
environment: environment:
no_proxy: ${no_proxy} no_proxy: ${no_proxy}
http_proxy: ${http_proxy} http_proxy: ${http_proxy}

2
CodeTrans/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -8,7 +8,7 @@ services:
ports: ports:
- "8008:80" - "8008:80"
volumes: volumes:
- "${MODEL_CACHE}:/data" - "${MODEL_CACHE:-./data}:/data"
shm_size: 1g shm_size: 1g
environment: environment:
no_proxy: ${no_proxy} no_proxy: ${no_proxy}

2
CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -8,7 +8,7 @@ services:
ports: ports:
- "8008:80" - "8008:80"
volumes: volumes:
- "${MODEL_CACHE}:/data" - "${MODEL_CACHE:-./data}:/data"
environment: environment:
no_proxy: ${no_proxy} no_proxy: ${no_proxy}
http_proxy: ${http_proxy} http_proxy: ${http_proxy}

2
DocSum/docker_compose/intel/cpu/xeon/compose.yaml
View File

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