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++
fused_gr: the persistent hyper-connection read's barrier only calls __nanosleep on sm_70 and newer (the sm_60 build of f-027-int2 failed on it)
Niko1221f1dadd171056
diff --git a/src/kernels/cuda/fused_gr.cu b/src/kernels/cuda/fused_gr.cuindex 6f6f32321..fe8672989 100644--- a/src/kernels/cuda/fused_gr.cu+++ b/src/kernels/cuda/fused_gr.cu@@ -2797,7 +2797,9 @@ __device__ __forceinline__ bool grid_sync(unsigned* bar, unsigned long long tickwhile (vb[32] == gen) {if (vb[48] != 0u) { ab = 1; break; }if (clock64() - t0 > (long long) ticks) { atomicExch(&bar[48], 1u); ab = 1; break; }- __nanosleep(64);+#if !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 700+ __nanosleep(64); // (sm_60 has no nanosleep: the barrier spins)+#endif}}if (vb[48] != 0u) ab = 1;