package modelplan import ( "math" "regexp" "strconv" ) // How fast a model answers on a CPU, from its size and the node's memory. // // Writing a token reads every weight it uses once, so on a CPU the memory // decides the speed: a token takes the bytes read over the rate llama.cpp // reads them at, plus a little that does not shrink with the model. // // The rate is the threads': each reads at about what one core reads alone, // a little less with every one added, up to what the whole machine reads. // On a server of many memory channels a replica given four threads reads at // a fraction of the machine's rate, and the machine's rate alone overstated // it several times. Measured on the PoC's node05 on 2026-11-03 (8 vCPU, // 43.9 GB/s with every CPU, 9.7 with one; llama-bench, 64 tokens): // // threads 1 2 4 8 // qwen2.5-coder-7b 1.9 3.6 6.3 9.3 tok/s 4.7 GB: 8.9 17.0 30.7 45.6 GB/s read // qwen2.5-1.5b 8.3 15.2 25.4 37.0 tok/s 1.1 GB: 9.7 18.3 32.6 — // // so 0.95 of one core's rate times threads^0.9, up to the machine's, and // 5 ms a token besides. Against what was measured before (2026-10-26): // node01's 1.5b on two threads, 14.5 tok/s, is taken for 15.0; node05's 14b // on four, 3.3, for 3.5. One reply at a time; several at once share the same // reads and each is slower. The PoC's host has far fewer cores than its VMs, // so these are what a busy host gives, and a machine of its own does better. // cpuReadShare is the part of the whole machine's rate llama.cpp reads at, // for a node whose one-core rate is not known: an agent older than its // measurement. const cpuReadShare = 0.68 // coreShare and threadExp are how threads add up: each about one core's // rate, a little less with every one added. const ( coreShare = 0.95 threadExp = 0.9 ) // cpuTokenFixed is a token's cost that does not grow with the model. const cpuTokenFixed = 0.005 // CPUTokensPerSecond is about how many tokens a second one reply gets on a // CPU whose memory reads bwGBs, from a model whose tokens each read bytes. // 0 when either is unknown. Use CPUTokensPerSecondOn where the threads and // one core's rate are known. func CPUTokensPerSecond(bytes int64, bwGBs float64) float64 { if bytes <= 0 || bwGBs <= 0 { return 0 } return 1 / (float64(bytes)/(bwGBs*1e9*cpuReadShare) + cpuTokenFixed) } // CPUReadGBs is the rate a replica given threads reads its weights at, on a // node whose memory reads allGBs with every CPU and coreGBs with one. Without // one core's rate or the threads, the share of the whole that small machines // gave. func CPUReadGBs(allGBs, coreGBs float64, threads int) float64 { if allGBs <= 0 { return 0 } if coreGBs <= 0 || threads <= 0 { return allGBs * cpuReadShare } return min(coreShare*coreGBs*math.Pow(float64(threads), threadExp), allGBs) } // CPUTokensPerSecondOn is about how many tokens a second one reply gets // from a model whose tokens each read bytes, on threads of a node whose // memory reads allGBs with every CPU and coreGBs with one. 0 when unknown. func CPUTokensPerSecondOn(bytes int64, allGBs, coreGBs float64, threads int) float64 { read := CPUReadGBs(allGBs, coreGBs, threads) if bytes <= 0 || read <= 0 { return 0 } return 1 / (float64(bytes)/(read*1e9) + cpuTokenFixed) } // CPUThreads is how many threads a CPU replica runs on: the cores its // profile reserves, else half the node's, which is what the agent gives // llama.cpp then. func CPUThreads(cpuCores, nodeCPUs int) int { if cpuCores > 0 { return cpuCores } return max(nodeCPUs/2, 1) } // Slow speeds: under the first a reply is a wait somebody notices, under the // second one of a few hundred tokens takes minutes. const ( CPUSlowTPS = 15 CPUTooSlowTPS = 5 ) // moeRead is what a token of a model of experts reads over its active // share. const moeRead = 1.6 // activeRE finds a model of experts' active parameters in its name, the // way they are written: Qwen3-30B-A3B, Ling-flash-A2.5B. var activeRE = regexp.MustCompile(`(?i)(?:^|[-_./])a(\d+(?:\.\d+)?)b(?:$|[-_.])`) // ActiveShare is the part of a model's weights one token reads: for a model // of experts named with its active parameters (…-30B-A3B) that over its // total, otherwise 1 — and 1.6 times that, which is what Qwen3-Coder-30B-A3B // read on cuda01's card (144 tok/s from 18.6 GB): the shared layers, the // embedding and the routing are read for every token whatever the experts. func ActiveShare(name string, params int64) float64 { m := activeRE.FindStringSubmatch(name) if m == nil || params <= 0 { return 1 } b, err := strconv.ParseFloat(m[1], 64) if err != nil || b <= 0 { return 1 } if s := moeRead * b * 1e9 / float64(params); s < 1 { return s } return 1 }