2.9.9-1

Fix crash when setting NCCL_MAX_P2P_NCHANNELS below nchannels.
Fix hang during sendrecv dynamic NVB connection establishment on
cubemesh topologies.
Add environment variable to only use SHARP on communicators beyond
a given number of ranks.
Add debug subsystem to trace memory allocations.
Fix compilation with TRACE=1. (Issue #505)

src/include/graph.h

@@ -26,6 +26,7 @@ ncclResult_t ncclTopoComputePaths(struct ncclTopoSystem* system, struct ncclPeer
 void ncclTopoFree(struct ncclTopoSystem* system);
 ncclResult_t ncclTopoTrimSystem(struct ncclTopoSystem* system, struct ncclComm* comm);
 ncclResult_t ncclTopoComputeP2pChannels(struct ncclComm* comm);
+ncclResult_t ncclTopoGetNvbGpus(struct ncclTopoSystem* system, int rank, int* nranks, int** ranks);
 
 // Query topology
 ncclResult_t ncclTopoGetNetDev(struct ncclTopoSystem* system, int rank, struct ncclTopoGraph* graph, int channelId, int rr, int* net);