ATC/vllm-legacy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update compose.yaml

Browse Source
This commit is contained in:
bart
2026-07-08 20:01:16 +02:00
parent 95e81de3cf
commit 979bf45764
1 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
compose.yaml
+10 -10
View File
@@ -2,6 +2,7 @@ services:
vllm-legacy: vllm-legacy:
image: vllm/vllm-openai:v0.4.0.post1 image: vllm/vllm-openai:v0.4.0.post1
container_name: vllm-legacy container_name: vllm-legacy
restart: unless-stopped
network_mode: host network_mode: host
ipc: host ipc: host
shm_size: "32gb" shm_size: "32gb"
@@ -20,16 +21,15 @@ services:
command: command:
- > - >
exec python3 -m vllm.entrypoints.openai.api_server exec python3 -m vllm.entrypoints.openai.api_server
--model "$$MODEL_PATH" --model ${MODEL_PATH}
--served-model-name "$$SERVED_NAME" --served-model-name ${SERVED_NAME}
--host 0.0.0.0 --port "$LISTEN_PORT" --host 0.0.0.0 --port ${LISTEN_PORT}
--tensor-parallel-size "$$TP_SIZE" --tensor-parallel-size ${TP_SIZE}
--dtype "$$DTYPE" --dtype ${DTYPE}
--max-model-len "$$MAX_MODEL_LEN" --max-model-len ${MAX_MODEL_LEN}
--gpu-memory-utilization "$$GPU_MEM_UTIL" --gpu-memory-utilization ${GPU_MEM_UTIL}
--max-num-seqs "$$MAX_NUM_SEQS" --max-num-seqs ${MAX_NUM_SEQS}
$$VLLM_EXTRA_ARGS ${VLLM_EXTRA_ARGS}
restart: "no"
volumes: volumes:
models: models: