Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
Fastino, a startup backed by Microsoft, has officially launched with $7 million in pre-seed funding to develop task-optimized AI models that operate without the need for GPUs. The company aims to provide high-performance enterprise AI solutions that run on CPUs, positioning itself as a competitor in the rapidly evolving AI landscape. Fastino's models are reported to be 1000 times faster than leading alternatives, potentially signaling a shift away from GPU reliance for AI-specific workflows. This launch comes amid growing interest in AI technologies that can deliver enhanced performance without traditional hardware constraints.
SambaNova extends its Llama 3.1 405B inference speed lead - achieving 163 output tokens/s, >2X other providers @SambaNovaAI has rolled out a speculative decoding on their 405B endpoint, now delivering speeds ranging up to 200 tokens/s (depending on prompt complexity). As we’ve… https://t.co/Vc1v8iYoDv
Reach for the stars with SambaNova Cloud! Unlock fast #AI inference on @AIatMeta's Llama 3.2 1B & 3B with unmatched performance — all running at full precision. Start building today ⤵️
The dominance of the GPU for AI-specific workflows might come to an end sooner rather than later. I'm now running Llama 3.1 8B Instruct at 1127 t/s and LLama 405B at 200 t/s! This is lightning fast! You can't get that speed anywhere else. The GPU was not designed for AI/ML, so… https://t.co/aD4UO2576q
