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 Windows: 64 Engram reader threads (each ReadFile is synchronous, so the threads are the queue depth); DS4_ENGRAM_THREADS overrides
Niko1221aee5db5eb1a9
diff --git a/src/dsv41/ds4_model.cu b/src/dsv41/ds4_model.cuindex 1eaeccebc..4b307a026 100644--- a/src/dsv41/ds4_model.cu+++ b/src/dsv41/ds4_model.cu@@ -2388,8 +2388,14 @@ struct Model::Impl {// the Engram rows' reader: threads enough to keep an SSD's queue busy (reads from the page cache need few);// the row cache a small share of the RAM free (DS4_ENGRAM_CACHE_MB: its size, 0 off; DS4_ENGRAM_THREADS)const size_t row = (size_t) pk.eg_hd + pk.eg_hd / 32;+#if defined(_WIN32)+ // (Windows: each thread's ReadFile is synchronous, so the threads are the queue depth - a 28K-token prompt+ // in one chunk, 1.36M rows before layer 1: 10 threads 17.1 s, 32 14.1 s, 64 13.4 s on a 20-core PC)+ int nth = 64;+#elseconst unsigned hw = std::max(1u, std::thread::hardware_concurrency());int nth = (int) std::min(16u, std::max(4u, hw / 2));+#endifif (const char* e = std::getenv("DS4_ENGRAM_THREADS")) nth = std::max(1, std::atoi(e));const uint64_t avail = ram_avail();uint64_t mb = avail == ~uint64_t{0} ? 64 : std::min<uint64_t>(256, std::max<uint64_t>(16, (avail >> 20) / 64));