{"contentHash":"5219e851084e67f8a9b74a457d6c602ad123b51f37ef1ee81c123d7a6f47174d","protocol":"bitcoin","authorPubkey":"d0617d73450b1755bcbaf94933002f8a6bd007938e8e5a645ea5481bbe4eac11","text":"Why were people harping on about llama.cpp's --moe-cache-mib? It seems to be useless. The decode speed is slightly worse than if I just manually tuned --n-cpu-moe and the prefill is much worse. I did pull and rebuild the commit from about an hour ago where they changed the algorithm, doesn't seem to have gotten much better. --n-cpu-moe is still superior.","topicHash":"913c62c2ee31793c7e8517600dbc8f0c337afae133700a128a7d8ffb8a21c93e","topicName":"technology","parentHash":"297b2c729cee5fd3fd445e4df199d16b5e02d3d791ff7e0778cb4263477aa27f","costSunk":"0","biasSupport":0,"biasOppose":0,"biasVouch":0,"biasNull":0,"blockHeight":null,"confirmations":0,"timestamp":"2026-11-06T13:06:52.746Z","tripFp":"7076ceffbf16","viewCount":0,"powDifficulty":0,"relation":0,"ephemeral":true,"nonce":"dfc379af6424b6cc","sig":"c1defdd607beb6ff65507097c091744dbac969c52353268a865197868cf39022432811902dc1e83bbd4b96f6334d589908cce5d8ac1697ad843a9c95c887bc41","ephStamp":{"blockHashHex":"0000000000000000000165e4531c467a5eaf29dddf030ff69bbfe810daa1bfa3","nonceHex":"752a000000000000"},"replyCount":1,"chainReplyCount":0,"vaporReplyCount":1,"clusterSize":2,"receiptHeight":974809,"expiryHeight":976969,"authorMarks":{"since":"2026-11-06T13:06:52.778Z","via":"sight","inscribed":0,"likes":0,"biases":0},"lang":"en","servedBy":{"host":"6af58b1822e0cabfe57d76540f745d059b438f489a796ec6a705c6540233845e","t":"2026-11-08T20:20:34.664Z","sig":"552fb62889bf5cafab4ef84c0b67518c4c34e0715b902cb47f21ca7ec1ede16efbdaaedaba51e10f7c9302a2ef1698f6e0db0696c8b38b7d0695914d03a760d3","h":"00000000000000000001c6fee9ce4c94f2939fc431bac9a783a15f129c2c58b1"}}