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++

Merge f-148-amd (2053388dc, without the IQ2 fused default) into f-split-int2

Niko1221af3770c6b076
diff --cc src/prefill/moe_fused_iq.cu
index 4e3dc24e7,877906400..6eeb21db6
--- a/src/prefill/moe_fused_iq.cu
+++ b/src/prefill/moe_fused_iq.cu
@@@ -1410,12 -1412,10 +1412,12 @@@ bool native_supported(int gu_type, int
if (env < 0) {
if (gu_type != T_IQ2_S && gu_type != T_IQ3_XXS && gu_type != T_IQ3_S && gu_type != T_IQ4_XS) return false;
const DevInfo& d = dev_info();
- return d.ok && d.s120 && !d.t75 && d_covered_on(d_type, d);
+ // 12.0 cards with 80+ SMs only (RTX PRO 5000 / 6000, RTX 5080 / 5090): on an RTX 5070 (48 SMs, IQ2_XS pack, experts
+ // partly in RAM) the fused kernels were 4.7% slower on 20K prompts (0/6 pairs) - it keeps MMQ unless STRATA_PF_FUSED=1
+ return d.ok && d.s120 && d.sms >= 80 && !d.t75 && d_covered_on(d_type, d);
}
#endif
- if (env < 0 && gu_type != T_IQ3_S && gu_type != T_IQ3_XXS) return false; // default: only these two
+ if (env < 0 && gu_type != T_IQ3_S && gu_type != T_IQ3_XXS && gu_type != T_Q2_0) return false; // default: only these three
const DevInfo& d = dev_info();
if (!d.ok || !d_covered_on(d_type, d)) return false;
if (d.t75 && (gu_type != T_Q2_0 || d_type != T_Q2_0)) return false;