{"type":"video","version":"1.0","html":"<iframe width=\"560\" height=\"315\" sandbox=\"allow-same-origin allow-scripts allow-popups allow-forms\" title=\"KV cache streaming - the llama.cpp fork that enables Qwen 3.8 27B at large contexts for 16GB VRAM GPU owners\" src=\"https://video.troed.se/videos/embed/x2AxNGkvy21GbTX9MZ3A9S\" style=\"border: none\" allow=\"fullscreen\"></iframe>","width":560,"height":315,"title":"KV cache streaming - the llama.cpp fork that enables Qwen 3.8 27B at large contexts for 16GB VRAM GPU owners","author_name":"Miscellaneous","author_url":"https://video.troed.se/video-channels/misc","provider_name":"PeerTube","provider_url":"https://video.troed.se","thumbnail_url":"https://video.troed.se/lazy-static/thumbnails/955121a4-f0a5-4900-8ecc-f75d506c8643.png","thumbnail_width":1280,"thumbnail_height":720}