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.


[ROCm/rccl commit: d97a32fac8]

projects/rccl/src/include/gdrwrap.h

@@ -243,7 +243,7 @@ static ncclResult_t ncclGdrCudaFree(void* gdrHandle) {
   gdr_mem_desc_t *md = (gdr_mem_desc_t*)gdrHandle;
   NCCLCHECK(wrap_gdr_unmap(ncclGdrCopy, md->gdrMh, md->gdrMap, md->gdrMapSize));
   NCCLCHECK(wrap_gdr_unpin_buffer(ncclGdrCopy, md->gdrMh));
-  CUDACHECK(cudaFree(md->gdrDevMem));
+  NCCLCHECK(ncclCudaFree(md->gdrDevMem));
   free(md);
 
   return ncclSuccess;