Skip to content

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++
157 B
Raw Blame
#pragma once
// CUDA spelling used by the attention kernels; included only in HIP builds.
#include <hip/hip_math_constants.h>
#define CUDART_INF_F HIP_INF_F