vLLM | NVIDIA NGC

NVIDIA

vLLM

Container

NVIDIA

vLLM

vLLM is a fast and easy-to-use library for LLM inference and serving. The NVIDIA vLLM NGC Container is optimized for GPU acceleration, and contains a validated set of libraries that enable and optimize GPU performance.

Layer	Label		Created
844a57683b82c201cb02dd02ea2348da4bf60d6a977c2707061febdb0bf546be	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace`	01/23/2026 4:03 PM UTC
8735f96609613d4ab5958adec7caf598ba204690baac42c97ef0a31e03ddc534	ARG	`NVIDIA_BUILD_REF=7889d972aa2216bdb05cca4b18e773ef68db1ab8`	01/23/2026 4:03 PM UTC
dc007d41f7d05a9c491a898096b7959c19489ba0a7be2e1dbd828ffcca35e91a	LABEL	`com.nvidia.build.id=257596322`	01/23/2026 4:03 PM UTC
16572ff5af7d7b3dd8ef961f73182b31f52ccc6bdaa58f7f7ddd645edee3ae67	ENV	`NVIDIA_BUILD_ID=257596322`	01/23/2026 4:03 PM UTC
897032ab1bdac26f0136a64a967e8803f4c7e4ed6f79ec4af850a862cee28bcc	ARG	`NVIDIA_BUILD_ID=257596322`	01/23/2026 4:03 PM UTC
a1f4402d3a8ea3135bd2236b29bfc43c367885eeff19260ed0bdcc874a43b784	ENV	`NVIDIA_VLLM_VERSION=26.01`	01/23/2026 4:03 PM UTC
0d5fc08442806e31bbda743fb1c20f5a066c03818137eccb2b7537ff5d14affe	ARG	`NVIDIA_VLLM_VERSION=26.01`	01/23/2026 4:03 PM UTC
884857ab1347d1e4e745b839c6eac8eeeb3c79340ca066c7b98fa48c3ab57613	LABEL	`com.nvidia.vllm.version=0.13.0+faa43dbf`	01/23/2026 4:03 PM UTC
3c89e6cb39e3ace1b27121257a1a224d479ee3b18831c5a437b6391bdaaaf564	ENV	`PATH=/usr/local/lib/python3.12/dist-packages/torch_tensorrt/bin:/usr/local/cuda/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin:/opt/tensorrt/bin`	01/23/2026 4:03 PM UTC
d02a9855f86d9d8d80b77c5b8b932e7f8599f66e29a520eb0c8b366649e43f84	ENV	`NVIDIA_PRODUCT_NAME=vLLM`	01/23/2026 4:03 PM UTC