2.18.1-1

Add support for IB SHARP to NVLS (NVLink SHARP algorithm).
Add NVLS+Tree algorithm.
Add support for memory management using cuMem* functions.
Use all NICs for Send/Receive operations on systems with more than
one NIC per GPU (#804).
Add ncclCommSplit primitive, with resource sharing option in config.
Fix alltoallv hang (#788)
Increase number of channels on H100 when we're not limited by NVLink.
Improve error reporting in case of IB failure, printing local and
remote ID (#779).
Add build option to allow compilation against RDMA includes instead
of dynamically loading IB verbs symbols (#802).
Fix context creation for progress thread (#803).
NET/IB: add option to use multiple QPs in round-robin mode.
Fix tree performance issue when NVB is disabled on HCM topologies.

src/include/cudawrap.h

@@ -11,6 +11,9 @@
 #include <cuda_runtime.h>
 #include "checks.h"
 
+// Is cuMem API usage enabled
+extern int ncclCuMemEnable();
+
 #if CUDART_VERSION >= 11030
 #include <cudaTypedefs.h>
 #else
@@ -85,6 +88,7 @@ DECLARE_CUDA_PFN_EXTERN(cuMemExportToShareableHandle, 10020);
 DECLARE_CUDA_PFN_EXTERN(cuMemImportFromShareableHandle, 10020);
 DECLARE_CUDA_PFN_EXTERN(cuMemMap, 10020);
 DECLARE_CUDA_PFN_EXTERN(cuMemRelease, 10020);
+DECLARE_CUDA_PFN_EXTERN(cuMemRetainAllocationHandle, 11000);
 DECLARE_CUDA_PFN_EXTERN(cuMemSetAccess, 10020);
 DECLARE_CUDA_PFN_EXTERN(cuMemUnmap, 10020);
 #if CUDA_VERSION >= 11070