Cortex Project Updates #121
Technical Updates 🤖Machine-Learning(ML), CortexVirtual Machine(CVM)Complete the function of coco, voc, cifar10 dataset loading;circom generator RightShift and MulScalar parameter alignment. Type annotations, Symbol type confusion fixes;Generate graph optimization, lose invalid nodes after topological sorting. scalar is integrated into op as an attribute, the original parameter is still output to input.json, fix circom compilation repair;Increase NLP model training, long sequence numerical pr...
Cortex Project Updates #126
ZKML2024-01-02 Publish [ZKML release 1.0.1] (https://github.com/CortexFoundation/tachikoma/commits/zkml-v1.0.1/) In this release, we implemented the general ZKML framework and passed the mnist model for test. 2024-01-16 Publish fixed commits for ZKML Fixed some classification models' quantization bugs, including mobilenet, squeezenet, etc.ZKCVMThe Cortex team has been closely following the latest zkEVM technology, which is one of the goals in the ZK trilogy (zkTX -> zkVM -> zkML). 2024-0...
Cortex Project Updates #111
Technical Updates 🤖Machine-Learning(ML), CortexVirtual Machine(CVM) & Model RepresentationTool(MRT) R&D MRT/CVMMRT updated the accuracy test code, adjusted and tested the model output results of the sampling dataAdjust the parameter setting of Calibrate Pass: absmax, fix the problem of FuseBatchnormRefactored the Quantiza Pass code and fixed the Infer Precision issueFixed the FixPoint Infer Type problem and added subgraph verification functionThe model parameters are adjusted to Int8, which ...
First decentralized world computer capable of running AI 🤖 and AI-powered Dapps ⚒. MainNet is out. Go #BUILD!🔥
Cortex Project Updates #121
Technical Updates 🤖Machine-Learning(ML), CortexVirtual Machine(CVM)Complete the function of coco, voc, cifar10 dataset loading;circom generator RightShift and MulScalar parameter alignment. Type annotations, Symbol type confusion fixes;Generate graph optimization, lose invalid nodes after topological sorting. scalar is integrated into op as an attribute, the original parameter is still output to input.json, fix circom compilation repair;Increase NLP model training, long sequence numerical pr...
Cortex Project Updates #126
ZKML2024-01-02 Publish [ZKML release 1.0.1] (https://github.com/CortexFoundation/tachikoma/commits/zkml-v1.0.1/) In this release, we implemented the general ZKML framework and passed the mnist model for test. 2024-01-16 Publish fixed commits for ZKML Fixed some classification models' quantization bugs, including mobilenet, squeezenet, etc.ZKCVMThe Cortex team has been closely following the latest zkEVM technology, which is one of the goals in the ZK trilogy (zkTX -> zkVM -> zkML). 2024-0...
Cortex Project Updates #111
Technical Updates 🤖Machine-Learning(ML), CortexVirtual Machine(CVM) & Model RepresentationTool(MRT) R&D MRT/CVMMRT updated the accuracy test code, adjusted and tested the model output results of the sampling dataAdjust the parameter setting of Calibrate Pass: absmax, fix the problem of FuseBatchnormRefactored the Quantiza Pass code and fixed the Infer Precision issueFixed the FixPoint Infer Type problem and added subgraph verification functionThe model parameters are adjusted to Int8, which ...
First decentralized world computer capable of running AI 🤖 and AI-powered Dapps ⚒. MainNet is out. Go #BUILD!🔥

Subscribe to Cortex Labs

Subscribe to Cortex Labs
Share Dialog
Share Dialog
<100 subscribers
<100 subscribers

Machine-Learning(ML), CortexVirtual Machine(CVM) & Model RepresentationTool(MRT) R&D
MRT/CVM
MRT implements Calibrator, FuseBatchNorm, FuseAvgPool Pass
MRT implements Sampling, Discretor, and Quantizer Pass, using symmetric linear discrete method to quantify the model
Implemented FixPoint Pass to export the model to TVM Relay Expr, all the data are shaped
Realized the disk import and export function of MRT internal Trace, and quickly imported the last running results
ZKRollUp
The ZkProver GPU code is merged and updated, and it takes an average of 6s to solve a 64-size block, which is 5 times faster
ZkMatrix front-end packaging optimization, asynchronous acceleration, CDN acceleration, etc.
Cortex Full Node
The model on the Cortex chain is archived to improve the data backup process, construct the NFT contract, and use stable diffusion to randomly generate pictures, and the NFT has been sent to the model and data address. The NFT contract address is: 0x60fA83Ea5dEC41f1D1a2724E06A40BE86aF325da
Cortex has built an IPFS storage platform for model data: https://cortex.infura-ipfs.io/ipfs/
Cortex Theseus: Pass block into collectLogs
Cortex Theseus: improve HTTP write timeout handling
Community Updates👨👩👦👦
Cortex new browser for basic functional testing;
Christmas NFT event planning;
NFT community game planning;
Continue to collect, translate, and original in-depth related content, NFT and DeFi and other fields, and try to develop a new community and media content operation mode;
Continue to pay attention to popular projects in the market and analyze project logic and economic models.
About Cortex 😇
Cortex’s main mission is to provide state-of-the-art machine-learning models on the blockchain in which users can infer using smart contracts on the Cortex blockchain. One of Cortex’s goals also includes implementing a machine-learning platform that allows users to post tasks on the platform, and submit AI DApps (Artificial Intelligence Decentralized Applications).
Cortex is the only public blockchain that allows the execution of nontrivial AI algorithms on the blockchain. MainNet has launched. Go build!
TestNet
| Block Explorer — Cerebro| Mining Pool | Remix Editor | Software |

Machine-Learning(ML), CortexVirtual Machine(CVM) & Model RepresentationTool(MRT) R&D
MRT/CVM
MRT implements Calibrator, FuseBatchNorm, FuseAvgPool Pass
MRT implements Sampling, Discretor, and Quantizer Pass, using symmetric linear discrete method to quantify the model
Implemented FixPoint Pass to export the model to TVM Relay Expr, all the data are shaped
Realized the disk import and export function of MRT internal Trace, and quickly imported the last running results
ZKRollUp
The ZkProver GPU code is merged and updated, and it takes an average of 6s to solve a 64-size block, which is 5 times faster
ZkMatrix front-end packaging optimization, asynchronous acceleration, CDN acceleration, etc.
Cortex Full Node
The model on the Cortex chain is archived to improve the data backup process, construct the NFT contract, and use stable diffusion to randomly generate pictures, and the NFT has been sent to the model and data address. The NFT contract address is: 0x60fA83Ea5dEC41f1D1a2724E06A40BE86aF325da
Cortex has built an IPFS storage platform for model data: https://cortex.infura-ipfs.io/ipfs/
Cortex Theseus: Pass block into collectLogs
Cortex Theseus: improve HTTP write timeout handling
Community Updates👨👩👦👦
Cortex new browser for basic functional testing;
Christmas NFT event planning;
NFT community game planning;
Continue to collect, translate, and original in-depth related content, NFT and DeFi and other fields, and try to develop a new community and media content operation mode;
Continue to pay attention to popular projects in the market and analyze project logic and economic models.
About Cortex 😇
Cortex’s main mission is to provide state-of-the-art machine-learning models on the blockchain in which users can infer using smart contracts on the Cortex blockchain. One of Cortex’s goals also includes implementing a machine-learning platform that allows users to post tasks on the platform, and submit AI DApps (Artificial Intelligence Decentralized Applications).
Cortex is the only public blockchain that allows the execution of nontrivial AI algorithms on the blockchain. MainNet has launched. Go build!
TestNet
| Block Explorer — Cerebro| Mining Pool | Remix Editor | Software |
Social Media
Telegram Groups
Social Media
Telegram Groups
No activity yet