GitLab

Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>

Signed-off-by: Faradawn Yang <73060648+faradawn@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: pvijayakrish <pvijayakrish@nvidia.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

Signed-off-by: Yan Ru Pei <yanrpei@gmail.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>

Publish `generation_config.json` from worker to ingress, as part of Model Deployment Card. That allows ingress to read key fields out of it. Gemma 3 4B+ has some important information that's only in there.

Need to reinstall the rdma-core and libibverbs to use RDMA devices.
Also, docker container can be built using a recent version of UCX for
EFA support.
Signed-off-by: Adit Ranadive <aranadive@nvidia.com>

feat: set model specific prompt templates in the multimodal config files, add documentation for multimodal example deployment (#1366)