Fix: p2p + collectives called by sequence error

Author: xu.wang

src/transport/p2p.cc

@@ -922,10 +922,12 @@ ncclResult_t ret = ncclSuccess;
           cudaStream_t hostStream, deviceStream;
           NCCLCHECKGOTO(ncclStrongStreamAcquire(ncclCudaGraphNone(), &comm->sharedRes->hostStream, /*concurrent=*/false, &hostStream), ret, fail);
           NCCLCHECKGOTO(ncclStrongStreamAcquire(ncclCudaGraphNone(), &comm->sharedRes->deviceStream, /*concurrent=*/false, &deviceStream), ret, fail);
-          if (regRecord->regIpcAddrs.devPeerRmtAddrs == NULL)
+          if (regRecord->regIpcAddrs.devPeerRmtAddrs == NULL) {
             NCCLCHECKGOTO(ncclCudaCallocAsync(&regRecord->regIpcAddrs.devPeerRmtAddrs, comm->localRanks, hostStream), ret, fail);
-          if (needUpdate)
             NCCLCHECKGOTO(ncclCudaMemcpyAsync(regRecord->regIpcAddrs.devPeerRmtAddrs, regRecord->regIpcAddrs.hostPeerRmtAddrs, comm->localRanks, hostStream), ret, fail);
+          } else if (needUpdate) {
+            NCCLCHECKGOTO(ncclCudaMemcpyAsync(regRecord->regIpcAddrs.devPeerRmtAddrs, regRecord->regIpcAddrs.hostPeerRmtAddrs, comm->localRanks, hostStream), ret, fail);
+          }
           NCCLCHECKGOTO(ncclStreamWaitStream(deviceStream, hostStream, comm->sharedRes->scratchEvent), ret, fail);
           NCCLCHECKGOTO(ncclStrongStreamRelease(ncclCudaGraphNone(), &comm->sharedRes->hostStream, /*concurrent=*/false), ret, fail);
           NCCLCHECKGOTO(ncclStrongStreamRelease(ncclCudaGraphNone(), &comm->sharedRes->deviceStream, /*concurrent=*/false), ret, fail);