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

src/include/graph.h

@@ -51,6 +51,8 @@ int ncclPxnDisable(struct ncclComm* comm);
 ncclResult_t ncclTopoGetPxnRanks(struct ncclComm* comm, int** intermediateRanks, int* nranks);
 ncclResult_t ncclGetLocalCpu(struct ncclTopoSystem* system, int gpu, int* retCpu);
 
+ncclResult_t ncclGetUserP2pLevel(int* level);
+
 #define MAX_XGMI_INTER_GPUS 4
 ncclResult_t ncclTopoGetIntraNetDev(struct ncclTopoSystem* system, int rank, struct ncclTopoGraph* graph, int channelId, int type, int64_t* id, int* dev);
 ncclResult_t ncclTopoGetLinkType(struct ncclTopoSystem* system, int cudaDev1, int cudaDev2, bool* isXGMI, int maxInter=MAX_XGMI_INTER_GPUS, int nInter=0, int *inter=nullptr);
@@ -81,7 +83,9 @@ ncclResult_t ncclTopoGetLocalNet(struct ncclTopoSystem* system, int rank, int ch
 ncclResult_t ncclTopoGetLocalGpu(struct ncclTopoSystem* system, int64_t netId, int* gpuIndex);
 ncclResult_t getLocalNetCountByBw(struct ncclTopoSystem* system, int gpu, int *count);
 
+// Allows for up to 32 NICs per node on GB200-NVL72
 #define NCCL_TOPO_MAX_NODES 64
+ncclResult_t ncclTopoGetLocal(struct ncclTopoSystem* system, int type, int index, int resultType, int locals[NCCL_TOPO_MAX_NODES], int* localCount, int* pathType);
 
 // Init search. Needs to be done before calling ncclTopoCompute
 ncclResult_t ncclTopoSearchInit(struct ncclTopoSystem* system);