2.19.4-1

Split transport connect phase into multiple steps to avoid port
exhaustion when connecting alltoall at large scale. Defaults to 128
peers per round.
Fix memory leaks on CUDA graph capture.
Fix alltoallv crash on self-sendrecv.
Make topology detection more deterministic when PCI speeds are not
available (fix issue #1020).
Properly close shared memory in NVLS resources.
Revert proxy detach after 5 seconds.
Add option to print progress during transport connect.
Add option to set NCCL_DEBUG to INFO on first WARN.

src/include/comm.h

@@ -299,7 +299,7 @@ struct ncclComm {
   // Flag to ask NCCL kernels to abort
   volatile uint32_t *abortFlag;
   volatile uint32_t *childAbortFlag;
-  volatile uint32_t *abortFlagRefCount;
+  uint32_t *abortFlagRefCount;
 
   // Device side of the communicator (for cudaFree's)
   struct ncclDevComm* devComm; // actually = &ncclDevCommAndChannels::comm
@@ -342,8 +342,6 @@ struct ncclComm {
   int nvlsRegSupport;
   /* sharable NVLS resource. */
   struct ncclNvlsSharedRes* nvlsResources;
-  struct ncclShmemCollBuff nvlsShmem;
-  void *nvlsShmemHandle;
 
   ssize_t channelSize; // User requested work size (bytes) for channel partitions