diff --git a/docker/Dockerfile.multi b/docker/Dockerfile.multi
index eeafc8f4a65..4381149eaf1 100644
--- a/docker/Dockerfile.multi
+++ b/docker/Dockerfile.multi
@@ -131,11 +131,8 @@ FROM ${DEVEL_IMAGE} AS release
 RUN mkdir -p /root/.cache/pip
 
 WORKDIR /app/tensorrt_llm
-COPY --from=wheel /src/tensorrt_llm/build/tensorrt_llm*.whl .
-RUN --mount=type=cache,target=/root/.cache/pip \
-    pip install tensorrt_llm*.whl && \
-    rm tensorrt_llm*.whl && \
-    pip cache purge
+RUN --mount=type=cache,target=/root/.cache/pip --mount=type=bind,from=wheel,source=/src/tensorrt_llm/build,target=/tmp/wheel \
+    pip install /tmp/wheel/tensorrt_llm*.whl
 
 COPY README.md ./
 COPY docs docs
diff --git a/jenkins/current_image_tags.properties b/jenkins/current_image_tags.properties
index bd46241e51d..a7048d4f477 100644
--- a/jenkins/current_image_tags.properties
+++ b/jenkins/current_image_tags.properties
@@ -11,6 +11,7 @@
 #
 # NB: Typically, the suffix indicates the PR whose CI pipeline generated the images. In case that
 #     images are adopted from PostMerge pipelines, the abbreviated commit hash is used instead.
+IMAGE_NAME=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm
 LLM_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.06-py3-x86_64-ubuntu24.04-trt10.11.0.33-skip-tritondevel-202508201630-pre-test
 LLM_SBSA_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.06-py3-aarch64-ubuntu24.04-trt10.11.0.33-skip-tritondevel-202508201630-pre-test
 LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-12.9.1-devel-rocky8-x86_64-rocky8-py310-trt10.11.0.33-skip-tritondevel-202508201630-pre-test