Merge remote-tracking branch 'nccl/master' into develop

2025-06-20 07:53:59 -05:00
parent 12315c259a 8171af656b
commit aaf023976a
136 changed files with 8510 additions and 5421 deletions
@@ -108,6 +108,12 @@ inline void ncclGroupCommJoin(struct ncclComm* comm) {
    struct ncclComm** pp = &ncclGroupCommHead;
    while (*pp != nullptr && comm->intraComm0 != (*pp)->intraComm0)
      pp = &(*pp)->groupNext;
+
+    // didn't find its clique, we need to insert it with ascending order based on commHash
+    if (*pp == nullptr) {
+      pp = &ncclGroupCommHead;
+      while (*pp != nullptr && (*pp)->commHash < comm->commHash) pp = &(*pp)->groupNext;
+    }
    comm->groupNext = *pp;
    *pp = comm;
    // Comms gets a new memory stack scope upon joining. Each task batched for