Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
dsv41 CPU lane: prefetch only the IQ experts' pages not in RAM (os::prefetch_cold); DS4_IQ_PF_ALL=1 as before
Niko1221e6e14f271424
diff --git a/src/dsv41/ds4_model.cu b/src/dsv41/ds4_model.cuindex 29f595368..4cd00c699 100644--- a/src/dsv41/ds4_model.cu+++ b/src/dsv41/ds4_model.cu@@ -5037,12 +5037,16 @@ struct Model::Impl {return;}const float lim = g.lim;- { // (os::prefetch, as above)+ { // (os::prefetch_cold, as above: the resident ones are left alone - on Windows the hint walks every page of a+ // range, ~0.13 ms an IQ2_XXS expert, on the lane's critical path before the first entry computes.+ // DS4_IQ_PF_ALL=1: every range, as before)std::vector<std::pair<const void*, size_t>> want;for (const Ent& en : ents)if (!store && (l.ram.empty() || l.ram[(size_t) en.e] < 0))for (int r = 0; r < 3; ++r) want.push_back({mx_mat(l, en.e, r), mx_part_bytes(l, r)});- os::prefetch(want);+ static const bool pf_all = std::getenv("DS4_IQ_PF_ALL") != nullptr && std::atoi(std::getenv("DS4_IQ_PF_ALL")) != 0;+ if (pf_all) os::prefetch(want);+ else os::prefetch_cold(want);}// the activations in c_xh's bytes, E 4 apart: token t's (t < kWin) at row t - quantized once, whatever number of// entries take it - then a row a slot (kWin + slot): a token past the window's input (none on the decode or