Cerebras · Blogs

Blogs listings from Cerebras on TechiSeek. 155 public listings.

• Introducing gigaGPT: GPT-3 sized models in 565 lines of code - Cerebras (Cerebras)
  GigaGPT is Cerebras’ implementation of Andrei Karpathy’s nanoGPT – the simplest and most compact code base to train and fine-tune GPT model…
• OpenAI GPT OSS 120B Runs Fastest on Cerebras (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• What is Appliance Mode? - Cerebras (Cerebras)
  We created Appliance Mode for simplicity, ease of use, and robustness in training massive natural language AI models on the Cerebras Wafer-…
• StackAI × Cerebras: enabling the fastest inference for enterprise AI agents (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• GLM-4.7 on Cerebras: Record-Speed AI Inference (Cerebras)
  See how Z.ai GLM-4.7 runs at approximately 1,000 tokens per second on Cerebras for coding, tool use, and responsive agentic AI workflows.
• Cerebras Announces Fine-Tuning on the Cerebras AI Model Studio - Cerebras (Cerebras)
  Announcing the addition of fine-tuning capabilities for large language models to our dedicated cloud service, the Cerebras AI Model Studio.
• Partner Spotlight: Armis + Cerebras Enable Teams Build and Secure Software Faster (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• Cerebras API Certification Partner Program for LLM API Providers (Cerebras)
  Cerebras inference - the fastest inference API for generative AI.
• More Pixels, More Context, More Insight! - Cerebras (Cerebras)
  The Cerebras architecture is designed to overcome the limitations of GPUs and allow users to train large computer vision models on high-res…
• GSK (Dreaming Big with Cerebras): Dr. Kim Branson - Cerebras (Cerebras)
  GSK discovered Cerebras when they did a survey and Cerebras caught their attention because ‘they use silicon you can use, and a technologic…
• Humanizing Digital Technology with Norby (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• An AI Chip With Unprecedented Performance To Do the Unimaginable - Cerebras (Cerebras)
  AI chips have made machine learning a reality. With unprecedented pace of demand increases the need for high performance and more efficient…
• Why Cyber Defense Needs Faster Inference (Cerebras)
  Learn how faster AI inference helps cybersecurity teams analyze threats, accelerate triage and response, and contain attacks before they sp…
• Announcing Cerebras Cloud @ Cirrascale, Democratizing High-Performance AI Compute - Cerebras (Cerebras)
  Sep 16 2021 Announcing Cerebras Cloud @ Cirrascale, Democratizing High-Performance AI Compute - Cerebras Gil Haberman, Sr.
• Linear Scaling Made Possible with Weight Streaming - Cerebras (Cerebras)
  In a single keystroke, Cerebras can scale large language models from a single CS-2 system to 192 CS-2s in a Cerebras Wafer-Scale Cluster.
• Cerebras May 2025 Newsletter (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• Alex - iOS Development with AI and Cerebras Inference (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• Sei AI - Revolutionizing Financial Services Support with Cerebras-Powered Agents (Cerebras)
  The performance gains from Cerebras have enabled Sei AI to expand its capabilities in ways that weren't previously possible.
• Why the AI Race Shifted to Speed​​​​ (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• Cerebras Pioneers Ethical AI Development through Collaborative AI Initiatives (Cerebras)
  Today, Cerebras proudly revealed our pivotal role as a founding member of the AI Alliance , an initiative orchestrated by IBM and Meta.
• How Cerebras serves GPT-5.6 Sol at up to 750 tokens per second (Cerebras)
  Learn how Cerebras serves OpenAI’s GPT-5.6 Sol at up to 750 output tokens per second—without shrinking the model or compromising intelligen…
• Beyond AI for Wafer Scale Compute: Setting Records in Computational Fluid Dynamics - Cerebras (Cerebras)
  Nov 17 2020 Beyond AI for Wafer Scale Compute: Setting Records in Computational Fluid Dynamics - Cerebras In collaborations with researcher…
• Variable Sequence Length Training for Long-Context Large Language Models - Cerebras (Cerebras)
  We show it is possible to accelerate the training for large language models with long context capabilities using a simple staged training m…
• Multi-Billion-Parameter Model Training Made Easy with CSoft R1.3 - Cerebras (Cerebras)
  CSoft R1.3 delivers GPT-J continuous pre-training, more reference model implementations in PyTorch and even faster training with Variable T…
• OpenAI Partners with Cerebras to Bring High-Speed Inference to the Mainstream (Cerebras)
  OpenAI and Cerebras signed a multi-year agreement to deploy 750 MW of wafer-scale systems, expanding low-latency AI inference beginning in…
• Cerebras Brings Trillion Parameter Inference to Enterprises with Kimi K2.6 (Cerebras)
  Run Kimi K2.6 at 981 output tokens per second in Cerebras enterprise trials, enabling real-time agentic coding and trillion-parameter AI wo…
• Cerebras CS-3 vs. Nvidia DGX B200 Blackwell (Cerebras)
  Compare Cerebras CS-3 and NVIDIA DGX B200 Blackwell on AI inference speed, cost, energy use, scaling, reliability and ecosystem tradeoffs.
• Cerebras Partners with IBM to Accelerate Enterprise AI Adoption (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• Realtime Reasoning is Here - Qwen3-32B is Live on Cerebras (Cerebras)
  May 15 2025 Realtime Reasoning is Here - Qwen3-32 B is Live on Cerebras Qwen3-32 B on Cerebras runs at 2,400 tokens/s, making reasoning run…
• Sandia Awards Major Contract to Cerebras Systems - Cerebras (Cerebras)
  Learn more about what impressed Sandia Labs about Cerebras Systems, and our past achievements in the intersection of artificial intelligenc…
• Cerebras at NeurIPS 2025: Nine Papers From Pretraining to Inference (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• Bringing Cerebras Inference to Quora Poe’s Fast Growing AI Ecosystem (Cerebras)
  Now live on Poe: Cerebras, delivering the fastest inference in the world.
• Cerebras February 2026 Highlights (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• Cerebras Software Release 2.0: 50% Faster Training, PyTorch 2.0 Support, Diffusion Transformers, and (Cerebras)
  R2.0 is the biggest software update to our platform this year, bringing a generational leap in performance, programmability, and model supp…
• Qwen3 Coder 480B is Live on Cerebras (Cerebras)
  Alibaba's Qwen3 Coder 480B Instruct model is now available on Cerebras.
• Scaling and Operationalizing AI in Government - Cerebras (Cerebras)
  Gil Haberman, Senior Director of Product Marketing Scaling and Operationalizing AI in Government Today at AI World Government 2021, Andy Ho…
• Jais: a New Pinnacle in Open Arabic NLP (Cerebras)
  Introducing a new state-of-the-art bi-lingual Arabic-English AI large language model.
• TotalEnergies and Cerebras Create Massively Scalable Stencil Algorithm - Cerebras (Cerebras)
  TotalEnergies used the Cerebras CS-2 system to turn a problem long accepted to be memory-bound into compute-bound.
• Customer Blog: Accelerating Drug Discovery with New AI Models - Cerebras (Cerebras)
  Products Developers Resources Company General Compute Selects Cerebras to Bring Ultra-Fast Inference to Agentic Coding >> Apr 26 2021 See t…
• SlimPajama: A 627B token, cleaned and deduplicated version of RedPajam (Cerebras)
  Slim Pajama was created by cleaning and deduplicating the 1.21 T token Red Pajama dataset from Together.
• Creating Sparse GPT-3 Models with Iterative Pruning - Cerebras (Cerebras)
  We have trained extremely sparse GPT-3 1.3B parameter models on the Cerebras CS-2 system, including an 83.8% sparse model with 3x reduction…
• Guii: An Interactive Coding Companion for Creative Frontend Development - Cerebras (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• EPCC Edinburgh (Projects on CS-1): Professor Mark Parsons June 2021 - Cerebras (Cerebras)
  EPCC has been using the Cerebras CS-1 for about a month and has already made tremendous progress.
• Can Sparsity Make AI Models More Accurate? (Cerebras)
  Cerebras introduces Sparse-IFT, a technique that, through sparsification, increases accuracy without increasing training FLOPs.
• Cerebras brings instant inference to Mistral Le Chat - Cerebras (Cerebras)
  Cerebras January update: Fastest DeepSeek R1-70B, Mayo Clinic genomic model, Davos appearance, and more!
• Key Insights from the 1st Multilingual Workshop - Cerebras (Cerebras)
  At NeurIPS 2023, we kicked off our inaugural workshop on multilingual models, where experts and enthusiasts alike converged to exchange ins…
• Supporting PyTorch on the Cerebras Wafer-Scale Engine - Cerebras (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• The Practitioner’s Guide to the Maximal Update Parameterization - Cerebras (Cerebras)
  Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
• First Look @ Gemma 4 on Cerebras: 3 Fast Multimodal Apps We Built (Cerebras)
  Build lightning-fast multimodal AI apps with Gemma 4 on Cerebras. Learn image understanding, vision workflows, and high-speed inference for…
• Introducing Cerebras CS-4: The Fastest AI Gets Faster (Cerebras)
  Meet Cerebras CS-4, a wafer-scale AI accelerator with up to 30× faster inference than GPU systems, native disaggregated inference and highe…