🔥 Trending today
DiffusionGemma: 4x Faster Text Generation★ 76
Hacker News (AI keywords)4 days agoReleaseGoogle released DiffusionGemma, a 26B MoE experimental open model using text diffusion instead of token-by-token autoregressive decoding. It can generate blocks of text in parallel, reaching up to 4x faster output on dedicated GPUs. The model targets local, speed-sensitive workflows, but Google says its output quality is below standard Gemma 4 and recommends Gemma 4 for quality-critical production use.
Hugging Face 聯手 Cloudflare：為開發者帶來無伺服器 GPU 推理服務★ 75
Hugging Face Blog803 days agoReleaseHugging Face and internet infrastructure giant Cloudflare have announced a major partnership that officially brings serverless GPU inference services to…