Filter by Category
- Corporate
- Product
- Developer
- AI
- Announcements
- Machine Intelligence
- Research
- Software
- IPU
- Natural Language Processing
- Case Studies
- Poplar
- NLP
- Machine Learning
- LLM
- Tutorials
- IPU-POD
- Large models
- Cloud
- Commentary
- Scientific Research
- Generative AI
- Computer Vision
- Graph Neural Networks
- Partners
- Drug Discovery
- GNN
- HPC
- University
- Benchmarks
- Memory
- Papers review
- Paperspace
- FP8
- Healthcare
- PyTorch
- Finance
- IPU-Machine
- Baidu
- Small Batch Training
- BERT
- Good Computer
- Podcast
- PopVision
- ResNeXt
- Dell
- Microsoft
- Microsoft Azure
- Mixture of Experts
- Sparsity
- Telecoms
- 5G
- Alibaba
- C600
- Careers
- Guest post
- Hugging Face
- Robotics
- Server
- Storage
- Tencent
Thinking Differently for World Quality Week
Graphcore to invest £1bn in India, creating 500 semiconductor jobs
July Papers: Subliminal Learning, Mixture of Recursions and Dataset Curation
June Papers: Gradient Norms, LLM Reasoning and Video Generation
May Papers: Parallel scaling, Evolving code, Understanding LLM reasoning
April Papers: Motion Prompting, Mamba Reasoning and Modeling Rewards
March Papers: De-Norming, Skill-Scaling, Over-Training, Drug-Generating
February Papers: Learning to Scale
January Papers: More Like “Reas-anuary Papers”
Spend Your FLOPs Wisely: December Papers
An LLM feast: November papers
Improving image generation and making LLMs think: October Papers
Graphcore begins hiring drive with 75 new jobs
Proper conditioning: September papers of the month
Hallucinations, Quantisations and Test-Time Computations: POTM August
All about scaling: July papers of the month
Graphcore joins Ultra Ethernet Consortium
Graphcore joins SoftBank Group to build next generation of AI compute
Mamba-2 & Matmul-free Models: June Papers of the Month
xLSTM, Schedule-Free Optimizers, Multi-token prediction: POTM May
Royal Society Fellowships for Graphcore’s Knowles and Fitzgibbon
TriForce, QuaRot, Mixture-of-Depths: Papers of the Month (Apr 2024)
Longer RoPEs and Better Quantisation: Papers of the Month (Feb 2024)
Great Teachers and Beyond Chinchilla: Papers of the Month (Jan 2024)
Graphcore Presenting FP8 research at NeurIPS 2023
IPU delivers 10X acceleration for DNA and protein sequence alignment
Gcore extends its IPU cloud offering to the USA
AI Safety Summit - First Do No Harm (Primum non nocere)
Deploy an API on Graphcore IPUs in less than 10 lines of code
Running Julia on Graphcore IPUs
Hadean turns to IPU to develop UK-sovereign AI capabilities for national security
Graphcore-Pienso partnership wins CogX Best Innovation: NLP Award
Graphcore joins the PyTorch Foundation
Making FP16 and FP8 easy to use with our new unit scaling library
Text summarization with BART Large on IPU
Fine-tune OpenAI's Whisper Automatic Speech Recognition (ASR) model
Llama 2: run Meta’s Open Source Large Language Model for free on IPUs
Fine-tuning Flan-T5 XXL - the powerful and efficient LLM
Graphcore expands AI tools ecosystem as UbiOps adds IPU support
Extending our PyTorch Geometric on IPUs support for large and heterogeneous graphs
Fraud detection using Graph Neural Networks with PyTorch Geometric
Graphium: an IPU-ready Python Library for training molecular GNNs at scale
Multitask Molecular Modelling with Graphium on the IPU
Gcore increases IPU cloud offering with new UK cluster
NLP Cloud adding IPU-powered models to its AI-as-a-Service platform
OpenAssistant fine-tuned Pythia-12B: open-source ChatGPT alternative
Flan-T5: sweet results with the smaller, more efficient LLM
Running Flan-T5-XL inference in Float16 for IPU - how we did it
Using generative AI commercially? Check it passes these three tests
Small language models, high performance: DeBERTa and the Future of NLU
PackedBERT: How to accelerate NLP tasks for Transformers with packing
Pienso offers efficient LLM access for business, powered by cloud IPUs
Argonne National Lab makes Bow IPUs available to researchers worldwide
Dolly 2.0 - open source language model with ChatGPT-like interactivity
How to use OpenAI’s Whisper for speech recognition
Accelerating Block Sparse Matrix Multiplication on IPUs with PopSparse
Accelerating PyG on IPUs: Unleash the Power of Graph Neural Networks
Getting started with PyTorch Geometric (PyG) on Graphcore IPUs
Graphcore users can now build and run GNNs with PyTorch Geometric
Open letter to the UK Prime Minister on investment in Exascale compute
Simple FP16 and FP8 training with unit scaling
How Graphcore's BERT breakthrough made Pienso's LLMs more efficient
Fine-tune GPT-J: a cost-effective GPT-4 alternative for many NLP tasks
Demo: How to fine-tune GPT-J for NLP tasks - text entailment example
Graphcore helps PNNL accelerate 3D molecular modelling with GNNs
Graphcore and Aleph Alpha partnership expands into semantic search
What GNNs are great at - and why Graphcore IPUs are great at GNNs
Paperspace and Graphcore launch ‘pay-as-you-grow' Gradient Notebooks
Rapidly building NLP applications with Hugging Face and IPUs
How to run Stable Diffusion Inference on IPUs with Paperspace
Poplar SDK 3.1 now available
Graphcore launches C600 PCIe card for AI compute
What's the Best AI Hardware for Graph Neural Networks?
Graphcore and Aleph Alpha demonstrate 80% sparsified AI model
Argonne National Laboratory adds Graphcore Bow IPU AI system
Getting started with Poplar Triton Backend
Preparing for the future of foundation models
Poplar SDK 3.0 now available
Getting started with TensorFlow Serving for IPU
Training large models more stably with automatic loss scaling
Compute giant HPE extends Graphcore’s global reach
Graphcore open-sources Argon Streams AV1 video decoder verification tool
Do neural networks dream of falling snow?
Paperspace and Graphcore partner to deliver free IPUs to developers
Deep dive: vision transformers on Hugging Face Optimum Graphcore
Getting started with IPUs on Paperspace
Pienso and Graphcore empower business with deeper, faster AI insights
Improving journey time predictions with GNNs on the Graphcore IPU
Poplar SDK 2.6 now available
Man Group unlocks massively parallel option pricing with Graphcore IPU
Graphcore's Groupbert research on show at ICML 2022 workshop
ETRI, Graphcore partner on high-efficiency software for large models
Graphcore and AMD propose FP8 AI standard with Qualcomm support
Baidu results underscore big MLPerf gains for Graphcore
Graphcore IPU powers brain-inspired deep learning at Kindai University
Computers for Superhuman Cognition: Simon Knowles at AICAS 2022
G-Core Labs IPU Cloud service now available
Accelerating and scaling temporal graph networks on the Graphcore IPU
Graphcore and Aleph Alpha partner on large, multi-modal AI models
EPCC - UK’s leading supercomputing centre - adds Graphcore IPU System
Graphcore to accelerate fusion energy research at Hartree Centre
Graphcore IPUs adopted in Argonne National Lab’s AI Testbed
Graphcore and Hugging Face launch new lineup of IPU-ready transformers
Poplar SDK 2.5 now available
Announcing Graphcore’s Accelerated Computing Academy
Graphcore and Tencent Cloud launch IPU Preview service
Lenovo servers now available for Graphcore IPU systems
Graphcore translates to price and performance gains for Twigfarm
Computing for Ultra-Intelligence: Simon Knowles at WAICF
LabGenius speeds up AI-based drug discovery with Graphcore IPUs
Accelerating Conversational AI with Gridspace and Graphcore
Optimising IPU Applications Using the PopVision Analysis Tools
Germany’s National HPC Centre at KIT installs Graphcore IPU system
AI for Simulation: how Graphcore is helping transform traditional HPC
The WoW Factor: Graphcore systems get huge power and efficiency boost
Graphcore announces roadmap to Ultra Intelligence AI Supercomputer
PNNL and Graphcore partner to advance AI for scientific research
Graphcore and NEC partner to deliver advanced AI compute
Graphcore and Spell launch partnership with free IPU test drive
Getting Started with Spell Workspaces and IPUs
G-Core Labs launches European AI cloud powered by Graphcore IPU
Building a better BERT: achieving 2x training speed with GroupBERT
Accelerating ResNet-50 Training on the IPU for MLPerf
Graphcore opens India office as nation embraces AI opportunity
Pure Storage and Graphcore release first reference architecture
Poplar SDK 2.4 now available
Sensoro chooses Graphcore IPU AI Technology for safer, greener towns and cities
Running End-to-End YOLO Object Detection on the IPU
Accelerating Computer Vision: scaling EfficientNet to large IPU-Pod Systems
Baidu PaddlePaddle now fully supported by Graphcore IPU
Get Started with Baidu PaddlePaddle on IPU Hardware
Microscopic World: Graphcore IPU powers DP Technology’s molecular dynamics simulation platform
Leveraging the IPU for Molecular Dynamics Simulation
Building Large Models on IPU
Exploiting Tile-Level Parallelism on Graphcore IPUs
Performance at Scale: Graphcore’s Latest MLPerf Training Results
Getting Started with Hugging Face Transformers for IPUs with Optimum
Why I’m joining Graphcore to lead our Developer Relations
Using the IPU to accelerate Spatial Interpolation Algorithm of Weather Data
Environmental AI: how the IPU is helping Agilor watch our water
Climate Change: Foreseeing the Unexpected with Graphcore IPUs
Graphcore Poplar SDK Container Images Now Available on Docker Hub
Differential Privacy and AI: Better Protecting Health Information with IPUs
Graphcore advances Scientific Research in New US Supercomputing Project
The Next Big Thing: Introducing IPU-POD128 and IPU-POD256
Graphcore releases Poplar SDK 2.3
VMware and Graphcore partner to bring AI resource disaggregation to enterprise environments
Graphcore advances in Southeast Asia with new Singapore base
Graphcore adds leading storage providers to Elite Partner Program
Hugging Face and Graphcore partner for IPU-optimized Transformers
Designing the Colossus Mk2 IPU: Simon Knowles at Hot Chips 2021
Poplar SDK 2.2 now available
Insuring success: Tractable accelerates accident and disaster recovery with Graphcore IPU
Graphcore opens Gdańsk office to strengthen R+D and customer support
Introducing the Initial Release of PyTorch Lightning for Graphcore IPUs
Getting Started with PyTorch Lightning for the IPU
Atos and Graphcore: bringing AI compute to the world
Introducing Packed BERT for 2x Training Speed-up in Natural Language Processing
Université de Paris accelerates Cosmology applications with Graphcore IPUs
Training Sparse, Large-Scale Language Models on Graphcore’s IPU
Graphcore IPUs to power Korea Telecom AI Data Centre
Raising the bar: Graphcore's first MLPerf results
What’s new for Developers in Poplar SDK 2.1?
Removing Batch Dependence in CNNs by proxy-normalising Activations
How we made EfficientNet more efficient
Graphcore turbocharges multi-horizon financial forecasting for Oxford-Man Institute
NHN chooses Graphcore for Korean AI Services
Colossus, Poplar and Tommy Flowers...
How to change the world with AI: Simon Knowles speaks on Pieter Abbeel Podcast
Graphcore talks Scaling up AI on Weights and Biases Podcast
University of Bristol solves scientific supercomputing problems with IPU systems
BERT-Large Training on the IPU explained
Accelerating America with new Graphcore partners
Graphcore Japan hits the ground running with SCSK and HPC Systems
Graphcore dives deep into software architecture layers on Practical AI Podcast
Graphcore advances sparse compute in new EU research project
Graphcore poised for explosive growth in China with partner Digital China
Supermicro Ultra servers now available in Graphcore IPU-POD
Start your innovation journey with IPUs: Introducing the Graphcore IPU-POD16
Optimising AI Performance with Graphcore PopVision Analysis Tools
Graphcore announces Major Software Release Poplar SDK 2.0
Introducing Graphcloud: Graphcore’s MK2 IPU-POD AI cloud service with Cirrascale
Graphcore Academic Programme: supporting and accelerating AI innovation
Machine Intelligence Research Directions in 2021
Graphcore raises $222 million in Series E Funding Round
University of Massachusetts Accelerates COVID-19 Modelling on the IPU
Graphcore sets new AI Performance Standards with MK2 IPU Systems
Introducing the Production Release of PyTorch for the IPU
Growing Graphcore in Germany
Reinventing Accelerated Computing for AI: Graphcore at SC20
Training Neural Networks in Low-Dimensional Random Bases
Graphcore releases new Poplar SDK 1.3
Major Update Released for Poplar Application Analysis Tool
Graphcore announces support for ODLA
The Future of AI Chips lies in Software
Announcing Graphcore’s Global Partner Program
University of Bristol tackles Challenges in Particle Physics with Graphcore’s IPU
A New Architecture for AI-Powered Drug Discovery
Accelerating Text-To-Speech Models with the IPU
