{"version":"1.0","type":"rich","provider_name":"techandbusiness.org","provider_url":"https://techandbusiness.org","title":"ggml 1.0.0 adds FP8 support and breaks compatibility with older RPC peers","author_name":"techandbusiness.org · AI, Infrastructure","thumbnail_url":"https://opengraph.githubassets.com/398ed72e9316d12d32e3371787d19fb096c1afc67fd25fc61f9c70d69c03087c/ggml-org/ggml/releases/tag/v1.0.0","width":600,"height":400,"html":"<blockquote class=\"tb-newswire-embed\" style=\"max-width:600px;border-left:3px solid #22d3ee;padding:12px 16px;margin:0;font-family:-apple-system,system-ui,sans-serif;background:#09090b;border-radius:0 8px 8px 0;\">\n      <p style=\"margin:0 0 8px;font-size:10px;font-weight:600;letter-spacing:0.1em;color:#71717a;\">techandbusiness.org · AI, Infrastructure</p>\n      <p style=\"margin:0 0 8px;font-size:18px;font-weight:700;line-height:1.3;color:#fff;\"><a href=\"https://techandbusiness.org/newswire/BZFPGlUfrVcozu9BIP0v6f\" style=\"color:#fff;text-decoration:none;\">ggml 1.0.0 adds FP8 support and breaks compatibility with older RPC peers</a></p>\n      <p style=\"margin:0;font-size:14px;color:#a1a1aa;line-height:1.5;\">ggml 1.0.0 adds FP8 support on CUDA and new execution paths across hardware backends, according to its release notes.</p>\n    </blockquote>"}