Is this page helpful?

Release Notes for NVIDIA NeMo Retriever Reranking NIM#

This documentation contains the release notes for NVIDIA NeMo Retriever Reranking NIM.

Note

Some releases are labelled “Production Branch” or “(PB)”. Production Branches provide reliable, stable versions of the NIM. Non-production branch releases (sometimes called Feature Branch (FB) releases) contain the latest features, improvements, and optimizations.

Release 2.3.0#

This release adds support for NVIDIA DGX Spark to the nvidia/llama-nemotron-rerank-vl-1b-v2 NIM.

Highlights#

  • Added FP16 support for NVIDIA GB10 on DGX Spark.

  • Added aarch64/Arm64 container support for DGX Spark deployments.

  • The standard single-GPU Docker deployment workflow now supports DGX Spark. For details, refer to Get Started.

For details, refer to Support Matrix.

Known Issues#

  • cuDNN SDPA is unusable on NVIDIA GB10 (SM121).

Release 2.2.0#

Release 2.2.0 was intentionally skipped.

Release 2.1.0#

Release 2.1.0 was intentionally skipped.

Release 2.0.0#

This release represents a major runtime upgrade for the nvidia/llama-nemotron-rerank-vl-1b-v2 NIM that includes a new purpose-built reranking inference stack. Compared to earlier versions, the new runtime delivers higher throughput and lower latency across all supported GPU SKUs, smaller VRAM footprint, faster startup time, and smaller container size.

Note

The model, supported modalities (text | image | text_image), and API are unchanged.

Highlights#

This release contains the following key changes:

  • The runtime selects optimized CUDA kernels automatically at startup based on the GPU’s compute capability. No manual profile selection steps are required.

  • Added support for loading model artifacts from Hugging Face or NGC.

    • To use Hugging Face (default), set HF_TOKEN.

    • To use NGC, set NIM_ENGINE_MODEL_DOWNLOAD_PROVIDER=ngc and NGC_API_KEY.

  • The NIM_ENGINE_COUNT env var defaults to 1. For details, refer to Engine Count.

  • Added the SHOW_CONFIG environment variable. Setting SHOW_CONFIG=1 at runtime lists the environment variables configured for the NIM.

  • You can opt-in to gRPC by setting NIM_SERVER_GRPC_BIND_ADDR.

  • New environment variables. For details, refer to Environment Variables for NVIDIA NeMo Retriever Reranking NIM.

  • NIM_ENGINE_MODEL_NAME configures the model name returned in API responses. NIM_SERVER_SERVED_MODEL_NAME configures legacy served model aliases for /v1/models and request model matching.

  • Environment variables use the NIM_SERVER_*, NIM_PIPELINE_*, and NIM_ENGINE_* namespaces in this version. Earlier flat and Triton-era names are not accepted as aliases. Common migrations include the following:

    • NIM_HTTP_API_PORT is now NIM_SERVER_BIND_ADDR.

    • NIM_TRITON_GRPC_PORT is now NIM_SERVER_GRPC_BIND_ADDR.

    • NIM_MODEL_NAME is now NIM_ENGINE_MODEL_NAME.

    • NIM_SERVED_MODEL_NAME is now NIM_SERVER_SERVED_MODEL_NAME.

    • NIM_MODEL_DOWNLOAD_PROVIDER is now NIM_ENGINE_MODEL_DOWNLOAD_PROVIDER.

    • NIM_MODEL_PATH is now NIM_ENGINE_MODEL_PATH.

    • NIM_PRECISION is now NIM_ENGINE_PRECISION.

    • NIM_PRECOMPILE_ONLY is now NIM_ENGINE_PRECOMPILE_ONLY.

    • NIM_CUDA_DEVICE is now NIM_ENGINE_CUDA_DEVICE.

    • NIM_ADMISSION_SIZE is now NIM_PIPELINE_ADMISSION_SIZE.

    • NIM_MAX_BATCH_SIZE is now NIM_PIPELINE_MAX_BATCH_SIZE.

    • NIM_MAX_CHUNK_SIZE is now NIM_PIPELINE_MAX_CHUNK_SIZE.

    • NIM_MAX_SEQ_LEN is now NIM_PIPELINE_MAX_SEQ_LEN.

    • NIM_LOG_LEVEL is now RUST_LOG.

    • NIM_LOGGING_JSONL is now LOG_FORMAT=json.

    • NIM_NUM_MODEL_INSTANCES and NIM_TRITON_MODEL_INSTANCE_COUNT are now NIM_ENGINE_COUNT.

  • Triton-era environment variables that do not have a migration are not supported by this runtime.

Support Matrix and Compatibility Updates#

  • The supported optimized SKUs are the following. For details, refer to Support Matrix for NVIDIA NeMo Retriever Reranking NIM.

    • FP16 on: B200, RTX PRO 6000, H100, H200, L40S, A100, A10G, L4

    • FP8 on: H100, H200, RTX PRO 6000

  • The default precision is now FP16 when supported. Set NIM_ENGINE_PRECISION=fp8 to opt into FP8.

All Known Issues#

The known issues for NeMo Retriever Reranking NIM are the following:

Release Notes for Previous Versions#