2.18.3-1

Fix data corruption with Tree/LL128 on systems with 1GPU:1NIC.
Fix hang with Collnet on bfloat16 on systems with less than one NIC
per GPU.
Fix long initialization time.
Fix data corruption with Collnet when mixing multi-process and
multi-GPU per process.
Fix crash when shared memory creation fails.
Fix Avg operation with Collnet/Chain.
Fix performance of alltoall at scale with more than one NIC per GPU.
Fix performance for DGX H800.
Fix race condition in connection progress causing a crash.
Fix network flush with Collnet.
Fix performance of aggregated allGather/reduceScatter operations.
Fix PXN operation when CUDA_VISIBLE_DEVICES is set.
Fix NVTX3 compilation issues on Debian 10.


[ROCm/rccl commit: ea38312273]

projects/rccl/src/include/devcomm.h

@@ -129,6 +129,9 @@ struct ncclRing {
 };
 
 
+// The root of each tree only has one node down (+1 intra-node).
+#define NCCL_MAX_TREE_ARITY_TOP 2
+// Nodes inside the binary tree can have to two nodes down (+1 intra-node).
 #define NCCL_MAX_TREE_ARITY 3
 struct ncclTree {
   int depth;