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/collectives.h

@@ -50,11 +50,12 @@ struct ncclDevRedOpFull {
   MACRO_IF(undef, /*undefined*/, DECL5(func, algo, LL128,  devredop, type))
 
 #define DECL3(func, devredop, type, undef) \
-  DECL4(func, RING,    devredop, type, undef) \
-  DECL4(func, TREE,    devredop, type, undef) \
+  DECL4(func, RING,           devredop, type, undef) \
+  DECL4(func, TREE,           devredop, type, undef) \
   DECL4(func, COLLNET_DIRECT, devredop, type, undef) \
-  DECL4(func, COLLNET_CHAIN, devredop, type, undef) \
-  DECL4(func, NVLS,    devredop, type, undef)
+  DECL4(func, COLLNET_CHAIN,  devredop, type, undef) \
+  DECL4(func, NVLS,           devredop, type, undef) \
+  DECL4(func, NVLS_TREE,      devredop, type, undef)
 
 #if defined(__CUDA_BF16_TYPES_EXIST__)
 #define DECL2(func, devredop, undefForFloat) \