dank/serverAppConfigs
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

Fix serve-vllm-qwen36-dflash.sh: remove 'vllm serve' prefix (image entrypoint handles it)

Browse Source
This commit is contained in:
Frank committed 2026-08-08 12:15:31 -07:00
1 parent 4edcada2a8
commit 9c1f777423
1 file changed
+3 -2
Download Patch File Download Diff File Expand all files Collapse all files
scripts/serve-vllm-qwen36-dflash.sh
+3 -2
View File
@@ -32,6 +32,7 @@ echo ""
podman rm -f "${CONTAINER_NAME}" 2>/dev/null || true podman rm -f "${CONTAINER_NAME}" 2>/dev/null || true
# Run vLLM in Podman container (foreground mode for systemd) # Run vLLM in Podman container (foreground mode for systemd)
# Note: vllm/vllm-openai image has entrypoint "vllm serve", so we pass args directly
exec podman run --name "${CONTAINER_NAME}" \ exec podman run --name "${CONTAINER_NAME}" \
--device /dev/nvidia0 \ --device /dev/nvidia0 \
--device /dev/nvidiactl \ --device /dev/nvidiactl \
@@ -39,10 +40,10 @@ exec podman run --name "${CONTAINER_NAME}" \
--device /dev/nvidia-uvm-tools \ --device /dev/nvidia-uvm-tools \
--device /dev/nvidia-modeset \ --device /dev/nvidia-modeset \
-v "${GPU_LIBS}:/usr/lib/x86_64-linux-gnu:ro" \ -v "${GPU_LIBS}:/usr/lib/x86_64-linux-gnu:ro" \
-v "${HF_CACHE}:/root/.cache/huggingface:ro" \ -v "${HF_CACHE}:/root/.cache/huggingface" \
-p "${PORT}:${PORT}" \ -p "${PORT}:${PORT}" \
docker.io/vllm/vllm-openai:latest \ docker.io/vllm/vllm-openai:latest \
vllm serve "${MODEL}" \ "${MODEL}" \
--port "${PORT}" \ --port "${PORT}" \
--host "0.0.0.0" \ --host "0.0.0.0" \
--kv-cache-dtype "${KV_CACHE_DTYPE}" \ --kv-cache-dtype "${KV_CACHE_DTYPE}" \