AI推理速度「吊打」英伟达？爆火的Groq芯片是「何方神圣」？

How does Groq LPU work? (w/ Head of Silicon Igor Arsovski!)

this is the fastest AI chip in the world: Groq explained

AMA: 1000's of LPUs, 1 AI Brain. Scaling with the Fastest AI Inference

Groq API - 500+ Tokens/s - First Impression and Tests - WOW!

Groqの革新的なLPUチップアーキテクチャ：低レイテンシー・高効率の大規模言語モデル推論を実現する（2024-05）【論文解説シリーズ】

Untold story of AI’s fastest chip

Groq, a US artificial intelligence startulaunched an inference chip for large-scale cloud models

Sorry Sam, The FASTEST AI Chip is HERE (without $7T)!!!

ALCF AI Testbed Training: Groq Tensor Streaming Architecture

NVIDIA Blackwell 발표 후.... 우리가 아직도 더 빠르다는 Groq. NVIDIA에 혁신이 없다고 평가한 AI 클라우드 스타트업의 설계 반도체 LPU는 무엇이 다른가

ALCF AI Testbed Training: Groq Runtime

【英伟达GPU/Groq LPU专业评测】结果让人又喜又惊，英伟达GPU真的能被Groq秒杀？特斯拉在最重要的步骤上取得重大突破，又要吊打其他电动车，股价有救了？#美股 #特斯拉股票 #英伟达

Difference Between GPU and LPU in Simple Words

Stupéfiant ! Jamais vu une IA aussi rapide, Groq 18 x plus qu'OpenAI !

Seven Silicon Highlights from SC23. And a Llama

Hardware/Software AMA on Discord

ALCF AI Testbed Training: Large Language Models (LLMs) and Llama-2 7B Deep Dive

SORACOM Technology Camp 2018 | B2. 通信モジュール内蔵デバイス制作のための心構え

The AI Hardware Show 23E6: Vast.ai, Intel CPU Max, Perceive, Groq, Lightelligence, NeuReality