Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.getlimina.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Prerequisites

Please only run one container instance per machine. Running multiple containers results in vastly reduced performance.
The following prerequisites are required to run the container:
  • Container engine, such as Docker (can be installed using the official instructions)
  • (GPU only) Nvidia Container Toolkit with Nvidia driver version 515 or higher (can be installed using the following installation guide)
All other dependencies, such as CUDA are included with the container and don’t need to be installed separately.

​
System Requirements

The image comes in two different build flavours:
  • A compact, CPU-only container that runs on any Intel or AMD CPU and a container with GPU acceleration. The CPU container is highly optimised for the majority of use cases, as the container uses hand-coded AMX/AVX2/AVX512/AVX512 VNNI instructions in conjunction with Neural Network compression techniques to deliver a ~25X speedup over a reference transformer-based system.
  • A GPU container is designed for large-scale deployments making billions of API calls or processing terabytes of data per month.

​
Minimum Requirements

The minimum system requirements for the container image are as follows:
MinimumRecommended (Text only)Recommended (All Features)Recommended Request Concurrency
CPUAny x86 (Intel or AMD) processor with 7.5GB free RAM and 50GB disk volumeIntel Sapphire Rapids or newer CPUs supporting AMX with 16GB RAM and 50GB disk volumeIntel Sapphire Rapids or newer CPUs supporting AMX with 64GB RAM and 100GB disk volume1
GPUAny x86 (Intel or AMD) processor with 28GB free RAM. Nvidia GPU with compute capability 7.0 or higher (Volta or newer) and at least 16GB VRAM. 100GB disk volumeAny x86 (Intel or AMD) processor with 32GB RAM and Nvidia Tesla T4 GPU. 100GB disk volumeAny x86 (Intel or AMD) processor with 64GB RAM and Nvidia Tesla T4 GPU. 100GB disk volume16
Please visit the recommended concurrency levels page to set the number of concurrent requests optimally. The Limina image can also run on the new Apple chips, such as the M2. Performance will be degraded however, due to the Rosetta 2 emulation of the AVX instructions.

​
CPU

While Limina CPU-based container will run on any x86-compatible instance, the below cloud instance types give optimal throughput and latency per dollar:
PlatformRecommended Instance Type (Text only)Recommended Instance Type (All Features)
AzureStandard_E2_v5 (2 vCPUs, 16GB RAM)Standard_E8_v5 (8 vCPUs, 64GB RAM)
AWSm7i.xlarge (4 vCPUs, 16GB RAM)m7i.4xlarge (16 vCPUs, 64GB RAM)
GCPn2-standard-4 (4 vCPUs, 16GB RAM)n2-standard-16 (16 vCPUs, 64GB RAM)
In the event when a lower latency is required, the instance type should be scaled; e.g. using an m7i.2xlarge in place of a m7i.xlarge. While the Limina container solution can make use of all available CPU cores, it delivers best throughput per dollar using a single CPU core machine. Scaling CPU cores does not result in a linear increase in performance.

​
GPU

Similarly for the GPU-based image, Limina recommends the following Nvidia T4 GPU-equipped instance types:
PlatformRecommended Instance Type (Text only)Recommended Instance Type (All Features)
AzureStandard_NC4as_T4_v3 (4 vCPUs, 28GB RAM)Standard_NC8as_T4_v3 (8 vCPUs, 56GB RAM)
AWSg4dn.2xlarge (8 vCPUs, 32GB RAM)g4dn.4xlarge (16 vCPUs, 64GB RAM)
GCPn1-standard-8 + Tesla T4 (8 vCPUs, 30GB RAM)n1-standard-16 + Tesla T4 (16 vCPUs, 60GB RAM)