diff --git a/c/glm.c b/c/glm.c index cea69b7..1e10044 100644 --- a/c/glm.c +++ b/c/glm.c @@ -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);