NeuReality Software Development Kit V1.2 Release Notes
Release Date
March 15, 2025
Target Audience
This is a NeuReality SDK v1.2 release. This release is intended for organizations utilizing the NeuReality AI Inference Appliance and Cluster for datacenter or edge-based deployments.
The use of the SDK is subject to the Early Access Program Agreement, End Customer Agreement or similar written instrument executed by and between your organization and NeuReality (“License Agreement”).
What’s new in this release?
LLM Models
Llama 3.1 70B
Mixtral 8x7B 0.1
Operator library
JPEG decoding operator - functional mode
Deployment API
Promotion to Qualcomm AI Cloud SDK v.1.18.4
Tensor Debugging
Management API
Provisioning status - provisioning very large LLMs can be time-consuming. A new provisioning status API enables users to track the progress.
HTTPS - adding HTTPS support enables protecting sensitive information from eavesdropping and tampering. This is especially crucial for management end points handling sensitive operations.
BMC
A toolbox for speeding up the appliance setup
FRU information display is added
Updated time settings are propagated to all NR1-M cards
System events log is populated with all the relevant messages
Delivery Packages and Upgrades
NeuReality Software SDK is delivered as follows:
Software Package |
Delivery |
|---|---|
NR1 AI-CPU Platform |
Built In / NeuReality Software Artifactory |
NR1-M AI Inference Module Platform |
Built In / NeuReality Software Artifactory |
NR1-S AI Inference Appliance BMC |
Built In / NeuReality Software Artifactory |
Toolchain library (Deployment API) |
|
Client library (Serving API) |
|
Kubernetes plugins |
Documentation
Please visit the NeuReality Developer Portal for more information about NeuReality SDK, tutorials, API reference, videos, and events.
Known Limitations
# |
Description |
Workaround |
Temporary Limitation |
|---|---|---|---|
AV-4373 |
Auto-negotiation is frequently used in Ethernet networks to find the most efficient mode of operation for two linked devices. NR1-M module auto negotiation feature is not functional in the present release. |
The settings controlled by auto-negotiation (such as port speed and flow control configurations) should be manually configured to the desired values using the remote management interface (IPMI). |
Yes |
AV-4373 |
Dual port is not supported in NR1-M card. Single port mode is supported. |
NA |
NA |
AV-4183 |
NR1-M module supports an Ethernet port (port0) with speeds of 25Gbps and 50Gbps. |
NA |
NA |
AV-4181 |
Once the NR1-M module network interface is up, it cannot be brought down without an NR1-M module reboot. |
Changing the network MTU which requires bringing down the network interface requires rebooting NR1-M module to finalize the MTU change. |
NA |
ASAI-2304 |
PFC support |
Priority flow control (PFC) is not supported on NR1-M card network port. Avoid enabling this feature. |
|
ASAI-5172 |
Cannot deploy more than one compute graph/model on a single NR1-M module. |
NA |
Yes |
AV-3829 |
Large receive offload (LRO) is enabled for connections where the total header length, including the TCP constant header, exceeds 63 bytes. |
NA |
Yes |
ASAI-7553 |
Non-contiguous arrays are not supported in NeuReality programming model and Deployment API. Using non-contiguous arrays will not be flagged as an error by the compiler, leading to run time errors during simulation or device execution. |
User code must avoid creating non-contiguous arrays. Input and output arrays submitted to the Deployment API should be contiguous in memory. For details on generating a contiguous array, please refer to the following: NumPy v2.0 Manual |
Yes |
ASAI-9194 |
Models over 70B parameters cannot be provisioned from SSD. |
Use remote provisioning from S3. |
Yes |
How to Get Help
Need a Hand? We’ve Got You Covered. Create a ticket with us, and let’s tackle those challenges together. Use one of the following channels to raise the issue: