serve: print the KV prefix-reuse diagnostic in mux mode too — [API] KV slot line existed only in the legacy \x02PROMPT path (#153)

2026-07-15 14:31:36 +08:00
parent a8895f2d84
commit d04d99e039
1 changed files with 1 additions and 0 deletions
@@ -4070,6 +4070,7 @@ static int mux_submit(Model *m, Tok *T, ServeCtx *ctx, ServeReq *req, int nctx,
        kv_disk_truncate(m,sc->len); }
    int add=nt-sc->len;
    if(add>0) memcpy(sc->hist+sc->len,tmp+sc->len,(size_t)add*sizeof(int));
+    fprintf(stderr,"[API] KV slot %d prefix %d/%d token, prefill %d\n",sub.slot,sc->len,nt,add);
    free(tmp);
    float *logit = add>0 ? step(m,sc->hist+sc->len,add,sc->len)
                         : step(m,sc->hist+sc->len-1,1,sc->len-1);