Merge pull request #420 from JustVugg/p417-metal-lfru

metal: advance the LFRU recency clock on the GPU-prerouted decode path (#417)
2026-07-19 15:02:41 +02:00
parent ebc851edb3 cfcc742591
commit 8f33bd153b
1 changed files with 5 additions and 0 deletions
@@ -2931,6 +2931,11 @@ static void moe(Model *m, Layer *l, int layer, float *x, int S, float *out, int
                m->eusage[layer][idxs[(int64_t)s*K+kk]]++;
                ehit_mark(m,layer,idxs[(int64_t)s*K+kk]);
                if(m->eheat[layer][idxs[(int64_t)s*K+kk]]<UINT32_MAX) m->eheat[layer][idxs[(int64_t)s*K+kk]]++;
+                /* #417: la scorciatoia GPU-prerouted deve far avanzare l'orologio di recency
+                 * come il percorso router completo (riga ~3055), altrimenti elast/eaccess_clock
+                 * si congelano a fine prefill e il tie-breaker LFRU di REPIN gira su punteggi
+                 * stantii durante il decode su Metal. */
+                m->elast[layer][idxs[(int64_t)s*K+kk]]=++m->eaccess_clock;
            }
            for(int d=0;d<D;d++) out[(int64_t)s*D+d]=0;
        }