[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-gpu-inference":3},{"tag":4,"articles":10,"peer_article_count":35},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"31748ccb-8b4d-4d50-a4cd-65aa6d0bf8be","GPU inference","gpu-inference",2,null,[11,20,28],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"49dbda12-d94e-4e41-99d0-200d57eb97a9","turboquant-vllm-kv-cache-3bit-storage-en","TurboQuant turns vLLM KV cache into 3-bit storage","I break down TurboQuant’s vLLM cache compression and give you a copy-ready setup for 3-bit KV cache and fallback paths.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779286502445-214g.png","en","2026-05-20T14:14:37.831446+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":25,"image_url":26,"cover_image":26,"language":18,"created_at":27},"b6caa87d-6766-486b-b510-0b27c6222f8e","nvidia-b300-vs-h200-deepseek-perf-en","NVIDIA B300 vs H200: Specs and DeepSeek Perf","B300 packs 288GB HBM3e and up to 8TB\u002Fs bandwidth. Here’s how it compares with H200 for DeepSeek inference and cloud costs.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775161683086-zo6y.png","2026-04-02T20:27:39.316088+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":16,"image_url":33,"cover_image":33,"language":18,"created_at":34},"b2de41c7-a1bf-414d-b843-97a3d0d1283b","turboquant-fast-cold-starts-rust-gpu-en","TurboQuant, Fast Cold Starts, and Rust on GPUs","TurboQuant cuts KV cache use 4.6x, GPU state restoration slashes cold starts, and Rust is moving deeper into CUDA work.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775146375773-h6or.png","2026-04-02T16:12:38.879237+00:00",0]