Support Matrix

These support matrices list the supported hardware and software requirements of Riva.

Riva 2.19.0

Hardware Compatibility

	Data Center (x86)	Embedded (aarch64)
Operating System	Riva server requires Linux x86_64 or Linux aarch64.	Riva server requires L4T aarch64.
GPU Model	Preferred Deployment Platforms: NVIDIA Blackwell NVIDIA H100 GPU NVIDIA L4 GPU NVIDIA L40 GPU NVIDIA A100 GPU NVIDIA A30 GPU NVIDIA A10 GPU NVIDIA Turing T4 Note Riva is supported on any NVIDIA Turing or later GPU for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+ GB VRAM is recommended.	Deployment Platforms: NVIDIA Jetson Orin
Jetson SDK version		JetPack 6.0

Software Compatibility

	Data Center (x86)	Embedded (aarch64)
Container	Container OS Ubuntu 24.04 CUDA 12.8.61 cuDNN 9.7.0.66 TensorRT 10.8.0.43 Triton Inference Server 2.54.0	Container OS Ubuntu 22.04 CUDA 12.2.140 cuDNN 9.5.1.17 TensorRT 10.6.0.26 Triton Inference Server 2.50.0
Docker	Docker > 19.02 with nvidia-docker installed For users other than DGX, Docker >= 19.03 is required. Note For DGX users, refer to Preparing to use NVIDIA Containers.	Docker >= 19.03 with nvidia-docker installed
MIG (Multi Instance GPU)	Deployment on MIG devices is possible on supported GPUs, provided enough resources are available as per the selected models. Note For further information, refer to MIG User Guide.
NeMo	NeMo 1.1.0 or later
Helm	Helm charts 3.x
NVIDIA Driver	510+ 418.40+, 440.33+, 450.51+, 460.27+, 470.57+ for Data Center GPUs Note For earlier driver versions, refer to the NVIDIA Driver section in Deep Learning Frameworks Support Matrix.

Model Information

Service	Model	Batch Size	Inference Mode	CPU Memory (GB)	GPU Memory (GB)	Supported on Embedded devices
ASR	conformer-ctc	64	offline, streaming, streaming-throughput	2, 2, 2	5.8, 3.6, 4.2	✅
ASR	parakeet-0-6b-ctc	64	offline, streaming, streaming-throughput	3, 3, 3	5.8, 4, 5	✅
ASR	parakeet-1-1b-ctc	64	offline, streaming, streaming-throughput	5, 5, 5	6.7, 5, 5.9	✅
ASR	parakeet-1-1b-rnnt	64	offline	3	8.5	❌
ASR	canary-1b	8	offline	6.5	13.4	❌
ASR	canary-0.6b-turbo	8	offline	5.3	12.2	❌
ASR	whisper-large-v3	8	offline	4.3	12.5	❌
ASR	whisper-large-v3-turbo	8	offline	3.8	11.3	❌
NMT	megatron-1b	8	offline		9	✅
TTS	fastpitch-hifigan	8	offline, streaming		2	✅
TTS	magpie	8	offline, streaming		5.8	❌

Skills Clients

Riva Speech AI Skills clients do not require a local GPU and have minimal hardware requirements. Refer to Clients in a New Programming Language for creating client bindings in your programming language. The Python section describes the prebuilt Python bindings included in the Riva Quick Start package, which are also based on gRPC.