Tagged: inference

22 articles

Latest

Hugging Face and AWS launch one-line deployment for 10,000+ transformer models

Hugging Face Inference Endpoints cut model latency in half for this team

OpenAI's Jalapeño chip beats Nvidia superchips by up to 1.9x per watt

Cerebras CS-4 hits 4,400 tokens/sec per user, doubling CS-3 on same chip

Etched hits $21B valuation after Jane Street tests its AI chips

Groq raises $350M at half its old valuation after losing CEO to Nvidia

AMD buys AI chip startup Taalas to etch models directly into silicon, hits 17,000 tokens/sec

AMD buys Taalas to bake Llama 3.1 into silicon at 16,000 tokens per second

AMD buys Taalas to bake AI models into silicon, hitting 17,000 tokens/sec

Runware's shipping-container data pods slash AI inference costs without water

AMD and Cerebras team up to take on Nvidia's Groq LPUs together

Etched hits $10.3B valuation on $300M raise, claiming its AI chips run faster at lower voltage

Google's 'Frozen v2' chip hardcodes Gemini's structure for 10x faster AI

The chatbot era is dead: Open Responses aims to fix the agent mess

NVIDIA's single NIM container now deploys over 100,000 Hugging Face LLMs without manual config

Hugging Face’s async robot brains cut task time in half by never waiting to think

SGLang taps Hugging Face transformers as a backend, instantly unlocking models like Kyutai's Helium

Groq's LPU chips land on Hugging Face, bringing sub-100ms inference to open models

Hugging Face offloads VAE decoding to the cloud, slashing GPU memory for Flux and video models

Hugging Face's TGI adds vLLM and TRT-LLM backends to end the serving wars

Hugging Face kills HUGS microservice just 2 years after launch

Google TPUs Hit Hugging Face at $1.37/Hour, Targeting Llama and Mistral Deploys