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++
launch header: exl3.cu includes it for every backend; exl3_cpu kGemmK only off x86
Niko12215ed8ae03be72
diff --git a/src/dsv41/vendor/exl3.cu b/src/dsv41/vendor/exl3.cuindex e94ffd7b6..2cdbc074b 100644--- a/src/dsv41/vendor/exl3.cu+++ b/src/dsv41/vendor/exl3.cu@@ -19,8 +19,8 @@// NVIDIA GPUs before sm_80 (V100, T4, RTX 20) decode with v1.1.8's kernels instead (exl3_legacy.cu, use_legacy// below): this file's CUDA-core fallback was slower there (a V100 with EXL3-3.05bpw: decode 4.9 -> 4.4 tok/s). The// prompt path below is this file's on every GPU.-#if defined(STRATA_METAL)#include "../ds4_launch.h" // strata_ds4_launch: <<<>>> on CUDA and HIP, a dispatch on Metal+#if defined(STRATA_METAL)#include <ds4_metal_host.h>#endif#include "strata/dsv41/exl3.hpp"diff --git a/src/dsv41/vendor/exl3_cpu.cpp b/src/dsv41/vendor/exl3_cpu.cppindex b7a313fbc..ae953586f 100644--- a/src/dsv41/vendor/exl3_cpu.cpp+++ b/src/dsv41/vendor/exl3_cpu.cpp@@ -1,4 +1,4 @@-#if !defined(__AVX512F__)+#if !(defined(__x86_64__) || defined(_M_X64)) // (x86 defines it below, inside its guard)// the band GEMM's chunk width, defined here because the uses are outside the AVX-512 guardconstexpr int kGemmK = 256;#endif