2.19.1-1

Add local user buffer registration for NVLink SHARP.
Add tuning plugin support.
Increase net API to v7 to allow for device-side packet reordering;
remove support for v4 plugins.
Add support for RoCE ECE.
Add support for C2C links.
Better detect SHM allocation failures to avoid crash with Bus Error.
Fix missing thread unlocks in bootstrap (Fixes #936).
Disable network flush by default on H100.
Move device code from src/collectives/device to src/device.


[ROCm/rccl commit: f9c3dc251e]

projects/rccl/src/include/graph.h

@@ -8,7 +8,7 @@
 #define NCCL_GRAPH_H_
 
 #include "nccl.h"
-#include "devcomm.h"
+#include "device.h"
 #include <limits.h>
 #include <stdlib.h>
 #include <ctype.h>
@@ -112,6 +112,6 @@ ncclResult_t ncclTopoPostset(struct ncclComm* comm, int* firstRanks, int* treePa
 
 ncclResult_t ncclTopoTuneModel(struct ncclComm* comm, int minCompCap, int maxCompCap, struct ncclTopoGraph** graphs);
 #include "info.h"
-ncclResult_t ncclTopoGetAlgoTime(struct ncclInfo* info, int algorithm, int protocol, int numPipeOps, float* time);
+ncclResult_t ncclTopoGetAlgoTime(struct ncclInfo* info, int algorithm, int protocol, int numPipeOps, float* time, bool* backup = NULL);
 
 #endif