inaccel

Privacy Preserving ML + MLOps : Combining the best of 2 worlds to secure your ML models and your data during your ML lifecycle: github.com/inaccel/heflow #mlops #PPML @mlopscommunity #MachineLearning @MLflow

The easiest way to deploy privacy preserving ML on top of @MLflow : github.com/inaccel/heflow

@VitalikButerin It seems more and more applications are adopting #ZKP. But how these applications can face the increased processing power required by ZKP? Could this be the next killer applications for cluster of #FPGAs?

Ever wondered how specifically ZK-SNARKs are used to preserve privacy, including some of the non-obvious tricks like how to prevent double-spending, and what the limits of ZK-SNARKs are? This post tries to explain some of these ideas: vitalik.ca/general/2022/0…

InAccel's world's first end2end integration of #ZKP with FPGAs supports frameworks like #Circom, #gnark or #ZoKrates @zkproof @ZKcommunity

Today InAccel releases the first end-to-end integration of FPGAs with multiple, state of the art, ZK frameworks. ZK Playground (play.zkaccel.io ) is an interactive web-based development environment that allows anyone to test zkSNARK circuits on top of FPGAs. #ZKP

Our @_morphemic_ project Coordinateur Geir Horn kicking off in Conference room :)

Call for participation 2nd Workshop on DevOps support for Cloud FPGA platforms (cFDevOps21) on August 30 at FPL 2021 (@2021Fpl) Attendance is free. Program: cfdevops.github.io/cFDevOps21/ Registration: cfaed.tu-dresden.de/fpl2021/regist…

Follow our #horizon2020 Project @_morphemic_ talk at 11h30 at @ow2 #OW2con'21 on youtube.com/watch?v=Jcm08z… or on @RocketChat rocketchat.ow2con.org to ask us questions! See you in #MORPHEMIC chat room with @Y_Vergi and all the team!!! #CloudComputing #Innovationprojects #cloud

@TekStrategist @Google One of the larger barrier for the adoption of AI chips is the lack of frameworks that allows easy deployment, scaling and resource management Even you have the best AI chip, if you do not provide the required middleware for easy integration to frameworks noone is going to use it

A summary of some of the huge investments in AI chips from @Google, but not including Google's investment in its own TPUs. #AIHardwareSummit2020

Google's Dave Patterson ponts to the comparison of RISC in the 1980s to Domain SPecific Architectures today. Interesting perspective. #AIHardwareSummit2020

Check out my latest article: The need of an Accelerator Operating System linkedin.com/pulse/need-acc… via @LinkedIn

Accelerated Machine Learning Available from your browser using the power of FPGAs linkedin.com/pulse/accelera… via @LinkedIn

@_morphemic_ Glad to participate and contribute in this great project!

Do we have everything? Let's check: - MORPHEMIC ship with very reliable MELODIC engine. The ship with amazing ability to morph into various forms, depending on a deployment environment - 12 experienced partners on board - wide Horizon There we go! MORPHEMIC has just sailed out 😀

just published: Performance evaluation of cloud computing platforms for Machine Learning link.medium.com/2RpBQadmm2

just published: Deploying FPGAs from Git repos instantly using BinderHub link.medium.com/4bZPhnbO81

Speedup your applications with zero code changes: The seamless way to make FPGA accessible to the… link.medium.com/JhgxqdPHB1

just published: Accelerating Jupyter data science and HPC applications with FPGAs, instantly. link.medium.com/EqhoUHgEw1

Check this 1min video of InAccel FPGA acceleration of Spark ML on SQL Server 2019 Big Data Cluster on Azure Data Studio. 9x speedup on ML training with zero code changes on Azure Data Studio using Xilinx Alveo cards over kubernetes! youtube.com/watch?v=qu7ct_…

InAccel's ML Accelerators integrated with Xilinx Vitis linkedin.com/pulse/inaccels… via @LinkedIn

Meet us at @XilinxInc XDF in San Jose Oct 1-2 to see live the unique FPGA resource manager and the accelerated ML suite #alveo #xilinx #XDF2019 #FPGA #SanJose