Hackernews posts about Cerebras

Cerebras is a leading artificial intelligence (AI) chip designer and manufacturer that specializes in creating highly scalable and powerful AI processing units for various industries and applications.

1. Cerebras fastest host for DeepSeek R1 70B, 57x faster than Nvidia GPUs (venturebeat.com)
   15 points by hochmartinez 6 days ago | 2 comments
2. DeepSeek R1 70B now available on Cerebras (1,500 tokens/s) (cerebras.ai)
   4 points by henry_viii 6 days ago | discuss
3. Open Weights Like DeepSeek Running on Cerebras (Latest Oxide and Friends) [video] (www.youtube.com)
   1 points by brunohaid 2 minutes ago | discuss
4. Free AI API Key
   4 points by singularis 12 days ago | 5 comments
5. The state of "super fast inference" is frustrating
   4 points by 4k 7 days ago | 1 comments
6. 100x defect tolerance: How we solved the yield problem (cerebras.ai)
   331 points by jwan584 21 days ago | 179 comments
7. Celebrating Ten Years of Encrypting the Web with Let's Encrypt (2023) (www.eff.org)
   3 points by debo_ about 22 hours ago | discuss
8. Is open Source SaaS is just SaaS with better marketing
   6 points by pkrulz101 1 day ago | 2 comments
9. Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models (www.cerebras.net)
   567 points by asb almost 2 years ago | 232 comments
10. Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference (cerebras.ai)
    427 points by benchmarkist 3 months ago | 156 comments
11. Cerebras-GPT vs. LLaMA AI Model Performance Comparison (www.lunasec.io)
    263 points by freeqaz almost 2 years ago | 70 comments
12. AI chipmaker Cerebras files for IPO (www.cnbc.com)
    219 points by TradingPlaces 4 months ago | 135 comments
13. Cerebras Inference: AI at Instant Speed (cerebras.ai)
    174 points by meetpateltech 5 months ago | 72 comments
14. Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s (cerebras.ai)
    147 points by campers 3 months ago | 84 comments
15. 4T transistors, one giant chip (Cerebras WSE-3) [video] (www.youtube.com)
    118 points by asdfasdf1 11 months ago | 86 comments
16. Cerebras-GPT: Open Compute-Optimal Language Models Trained on Cerebras Cluster (arxiv.org)
    97 points by cs-fan-101 almost 2 years ago | 12 comments
17. Cerebras launches inference for Llama 3.1; benchmarked at 1846 tokens/s on 8B (twitter.com)
    95 points by _micah_h 5 months ago | 42 comments
18. Cerebras Trains Llama Models to Leap over GPUs (www.nextplatform.com)
    64 points by rbanffy 3 months ago | 33 comments
19. Cerebras's Condor Galaxy AI supercomputer takes flight carrying 36 exaFLOPS (www.theregister.com)
    21 points by rntn over 1 year ago | 5 comments
20. Cerebras WSE-3 Chip (www.cerebras.net)
    19 points by averylamp 11 months ago | 2 comments
21. Cerebras Release 2.0: 50% Faster Training, PyTorch 2.0, Diffusion Transformers (www.cerebras.net)
    16 points by rbanffy about 1 year ago | 7 comments
22. Cerebras Launches the Fastest AI Inference (inference.cerebras.ai)
    13 points by cs-fan-101 5 months ago | 1 comments
23. Cerebras and G42 Break Ground on Condor Galaxy 3, an 8 ExaFLOPs AI Supercomputer (www.cerebras.net)
    12 points by sizzle 11 months ago | discuss
24. Cerebras launches processor for AI theoretically equivalent to 62 Nvidia H100s (www.tomshardware.com)
    9 points by reqo 11 months ago | 2 comments
25. Opentensor and Cerebras announce BTLM-3B-8K, a leading 3B param. language model (huggingface.co)
    9 points by cs-fan-101 over 1 year ago | 2 comments
26. Show HN: CerebrasCoder – make websites in less than a second (cerebrascoder.com)
    8 points by stevekrouse about 2 months ago | 3 comments
27. A Look Inside the Cerebras CS-2 AI Accelerator [video] (www.youtube.com)
    8 points by rbanffy over 1 year ago | 1 comments
28. Cerebras and G42 Unveil Condor Galaxy 1, a 4 ExaFLOPS AI Supercomputer (www.cerebras.net)
    7 points by cs-fan-101 over 1 year ago | 4 comments
29. cerebras: 450 tokens/sec llama 3.1 70B (www.theregister.com)
    7 points by davidfiala 5 months ago | 2 comments
30. Cerebras releases its own open source GPT models (Apache 2.0 License) (huggingface.co)
    7 points by armcat almost 2 years ago | 1 comments
31. Cerebras runs Llama 3.1 70B at 2,100 tokens per second, live demo available (twitter.com)
    6 points by modeless 3 months ago | discuss
32. Cerebras Inference now runs Llama 3.1-70B at 2100 tokens/s (cerebras.ai)
    6 points by cs-fan-101 3 months ago | discuss
33. Cerebras launches 900000-core 125 PetaFLOPS wafer-scale processor for AI (www.tomshardware.com)
    6 points by webmaven 11 months ago | discuss
34. Cerebras Unveils Fastest AI Chip with Whopping 4T Transistors (www.cerebras.net)
    6 points by cs-fan-101 11 months ago | discuss
35. Cerebras S1 (www.sec.gov)
    5 points by coloneltcb 4 months ago | discuss
36. Cerebras Coder (cerebrascoder.com)
    4 points by handfuloflight about 2 months ago | 1 comments
37. Show HN: Cerebras-GPT-2.7B finetuned on Stanford Alpaca dataset (github.com)
    4 points by lxe almost 2 years ago | 1 comments
38. Cerebras S-1 (www.sec.gov)
    4 points by Alextigtig 4 months ago | discuss