{"pubkey":"430165f794115699bd93d88295fe92c7a51aafaa8d701bf0719c2d4d0b99d97c","posts":[{"contentHash":"514427326108b6bdf0e4565f5c4a2105332e39b8a3b453bd6c14a7314fe1f38f","protocol":"bitcoin","authorPubkey":"430165f794115699bd93d88295fe92c7a51aafaa8d701bf0719c2d4d0b99d97c","text":"How is /lmg/ using their new GPU cache commands in llmao.cpp with GLM 5.3 and Qwen Flash Next? What kind of results are you seeing? https://github.com/ggml-org/llama.cpp/pull/29887","topicHash":"913c62c2ee31793c7e8517600dbc8f0c337afae133700a128a7d8ffb8a21c93e","topicName":"technology","parentHash":"55b34ee8e38d23a7cd941ed3363a6fe204f5300ff249157f07128a9208b75584","costSunk":"0","biasSupport":0,"biasOppose":0,"biasVouch":0,"biasNull":0,"blockHeight":null,"confirmations":0,"timestamp":"2026-10-26T04:07:45.560Z","tripFp":"bfd781f54756","viewCount":0,"powDifficulty":0,"relation":0,"ephemeral":true,"nonce":"52241c7cf3b950e0","sig":"e936f0e35f87ba86ef33376cd7bf778393b115a9cad54fafb10cd8a535ac97072bc6c95f3f6f3afbe3a5e30e54c78ca4ca17231ff45d2b41893220e15c8c1be5","ephStamp":{"blockHashHex":"00000000000000000000c37cfb4da567d47c3fb0d6b712a7204c8bc78a9fa819","nonceHex":"3f8a000000000000"},"replyCount":1,"chainReplyCount":0,"vaporReplyCount":1,"clusterSize":2,"receiptHeight":973182,"expiryHeight":977502,"authorMarks":{"since":"2026-10-26T02:07:03.458Z","via":"sight","inscribed":0,"likes":0,"biases":0},"lang":"en"}],"nextCursor":null,"pageReceipt":{"host":"6af58b1822e0cabfe57d76540f745d059b438f489a796ec6a705c6540233845e","t":"2026-11-08T20:11:47.819Z","sig":"f7492e5c2141091fc9170ff2addba4ac850da9a29134ee717c07c818319d6258742255e8f76c70bf9ab92f8ee8368c51a6d8e1c528b21f548ef63228627cbe8e"},"marks":{"since":"2026-10-26T02:07:03.458Z","via":"sight","inscribed":0,"likes":0,"biases":0}}