NCCL 2.26.2-1

Profiler improvements
 * Add events for CUDA kernel start and end.
 * Allow network plugins to generate profiling events
 * Enable profiling on a per-operation basis, rather than per-communicator.
 * Add support for graph capturing.

Add implicit launch order
 * Allow to prevent deadlocks when using multiple NCCL communicators per
   device by implicitly ordering NCCL operations using the host program
   order. Disabled by default, set NCCL_LAUNCH_ORDER_IMPLICIT=1 to enable.
 * Add a complementary mechanism to detect host threads racing to launch
   to the same device. Enabled by default, set NCCL_LAUNCH_RACE_FATAL=0 to
   disable.

Optimize the PAT algorithm
 * Separate the computation and execution of PAT steps on different warps,
   allowing to run up to 16 PAT steps in parallel to significantly
   accelerate PAT and reduce its linear part.

Add support for setting QoS per communicator
 * Add a new trafficClass field to the communicator configuration, to
   allow the application to select a particular traffic class for a
   given communicator. The meaning of the traffic class is
   network-specific and should be set in accordance with the network
   configuration.
 * For the IB/RoCE plugin, existing config variables such as NCCL_IB_SL
   and NCCL_IB_TC take precedence.

Allow to enable GPU Direct RDMA specifically on C2C platforms
 * Disabled by default, set NCCL_NET_GDR_C2C=1 to enable.

Do not disable user buffer registration unless PXN is really used
 * Only disable UB when a communicator has more than one rank per
   node on any node.

RAS subsystem improvements
 * Report operation counts separately for each collective operation type.
 * Provide details about missing communicator ranks and reliably
   distinguish ranks that are no longer a given communicator's members
   (now reported as NOCOMM) from those that failed to respond.

Add support for timestamps to NCCL diagnostic messages
 * On by default for WARN messages; NCCL_DEBUG_TIMESTAMP_LEVELS can be
   used to enable them for other debug levels as well.
 * The format can be changed using the NCCL_DEBUG_TIMESTAMP_FORMAT config
   variable.

Reduce the memory usage with NVLink SHARP (NVLS)
 * Potentially save hundreds of MBs of device memory, considering the
   multicast buffer size granularity separately from the address alignment.

Update performance tuning for recent Intel CPUs
 * Improve algorithm/protocol selection on recent CPUs such as Emerald
   Rapids and Sapphire Rapids.

Improve channel scheduling when mixing LL and Simple operations.
 * Make LL operations account for 4x more traffic to ensure LL and simple
   operations complete at the same time.

Refactor the plugin code
 * Clean up and harmonize the support code across the network, tuner,
   and profiler plugins.

Add support for comment lines (starting with #) in the nccl.conf file
* Issue #1540.

Make user buffer registration problems print an INFO instead of a WARN.

Drop support for network plugin interface version 5.

Fix a race condition with split-shared communicators
 * NCCL could hang during connection setup if multiple communicators
   were grouped together that share resources.

Fix a performance regression when using NCCL_CROSS_NIC=1
 * NCCL would unnecessarily alternate rings, breaking the GPU-NIC
   associations.

Make GID index detection code more resilient
 * Dynamic GID detection code was giving up too soon if the
   detected index was not available (e.g., wasn't mapped to the
   container's sysfs).
 * Issues #1538, #1573.

Fix a race condition with non-blocking operation
 * Fix issue when creating a non-blocking communicator after a non-
   blocking collective operation on another communicator.

Fix shared memory usage on recent Blackwell GPUs.
 * Issues NVIDIA/nccl-tests#287, NVIDIA/nccl-tests#291, #1637.

Fix an error with NIC fusion and IB SHARP when recreating communicators
 * Disable the unloading of network plugins

Make the auto-merge failures in the NIC fusion non-fatal
 * This could happen when trying to merge IB and RoCE devices.

Fixes to ncclCommAbort
 * Fix hangs due to the progress thread spinning indefinitely on the
   network progress.
 * Reduce the abort time by up to two orders of magnitude.

Fix a crash when libnccl.so was dynamically unloaded
 * The RAS subsystem was missing a clean-up handler.

Fix a hang if the network plugin's test() call returns an error.

Fix a hang on heterogeneous architectures
 * Ensure we harmonize the tuning to avoid different tuning choices,
   causing a hang.

Fix double-free on failed ncclCommInitRank and ncclCommFinalize.

Fix a potential list traversal bug during a group launch of multiple
communicators
 * Issue #1599.

Unify the handling of NCCL configuration variables
 * Under rare circumstances, some variables specified in the config file
   could be ignored.


[ROCm/rccl commit: f44ac759fe]

projects/rccl/ext-net/example/nccl/net.h

@@ -2,14 +2,15 @@
  * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
  */
 
-#ifndef NCCL_NET_H_
-#define NCCL_NET_H_
+#ifndef NET_H_
+#define NET_H_
 
 #include <stdint.h>
 #include <stdlib.h>
 
 #include "common.h"
 #include "err.h"
+#include "net_device.h"
 
 #define NCCL_NET_HANDLE_MAXSIZE 128
 #define NCCL_MAX_NET_SIZE_BYTES (1*1024*1024*1024*1024L) //1TB
@@ -22,6 +23,9 @@
 // Maximum number of requests per comm object
 #define NCCL_NET_MAX_REQUESTS 32
 
+typedef ncclResult_t (*ncclProfilerCallback_t)(void** eHandle, int type, void* phandle, int64_t pluginId, void* extData);
+
+#include "net_v10.h"
 #include "net_v9.h"
 #include "net_v8.h"
 #include "net_v7.h"
@@ -31,4 +35,9 @@
 #include "net_v3.h"
 #include "net_v2.h"
 
+typedef ncclNet_v10_t ncclNet_t;
+typedef ncclNetProperties_v10_t ncclNetProperties_t;
+typedef ncclNetVDeviceProps_v10_t ncclNetVDeviceProps_t;
+typedef ncclNetCommConfig_v10_t ncclNetCommConfig_t;
+
 #endif // end include guard

projects/rccl/ext-net/example/nccl/net_device.h

@@ -26,6 +26,7 @@ typedef struct {
 
 typedef ncclNetDeviceHandle_v7_t ncclNetDeviceHandle_v8_t;
 typedef ncclNetDeviceHandle_v8_t ncclNetDeviceHandle_v9_t;
-typedef ncclNetDeviceHandle_v9_t ncclNetDeviceHandle_t;
+typedef ncclNetDeviceHandle_v9_t ncclNetDeviceHandle_v10_t;
+typedef ncclNetDeviceHandle_v10_t ncclNetDeviceHandle_t;
 
 #endif

projects/rccl/ext-net/example/nccl/net_v10.h

@@ -0,0 +1,101 @@
+/*
+ * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
+ */
+
+#ifndef NET_V10_H_
+#define NET_V10_H_
+
+#define NCCL_NET_MAX_DEVS_PER_NIC_V10 4
+typedef struct {
+  int ndevs;
+  int devs[NCCL_NET_MAX_DEVS_PER_NIC_V10];
+} ncclNetVDeviceProps_v10_t;
+
+
+#define NCCL_NET_TRAFFIC_CLASS_UNDEF -1
+typedef struct {
+  // Plugin-specific TC value
+  int trafficClass;
+} ncclNetCommConfig_v10_t;
+
+
+typedef struct {
+  char* name;                      // Used mostly for logging.
+  char* pciPath;                   // Path to the PCI device in /sys.
+  uint64_t guid;                   // Unique identifier for the NIC chip. Important for
+                                   // cards with multiple PCI functions (Physical or virtual).
+  int ptrSupport;                  // [NCCL_PTR_HOST|NCCL_PTR_CUDA|NCCL_PTR_DMABUF]
+  int regIsGlobal;                 // regMr is not tied to a particular comm
+  int forceFlush;                  // Force a flush on receives
+  int speed;                       // Port speed in Mbps.
+  int port;                        // Port number.
+  float latency;                   // Network latency
+  int maxComms;                    // Maximum number of comms we can create
+  int maxRecvs;                    // Maximum number of grouped receives.
+  ncclNetDeviceType netDeviceType; // Network offload type
+  int netDeviceVersion;            // Version number for network offload
+  ncclNetVDeviceProps_v10_t vProps;
+  size_t maxP2pBytes;              // Max transfer size for point-to-point operations
+  size_t maxCollBytes;             // Max transfer size for collective operations
+} ncclNetProperties_v10_t;
+
+typedef struct {
+  // Name of the network (mainly for logs)
+  const char* name;
+  // Initialize the network.
+  ncclResult_t (*init)(ncclDebugLogger_t logFunction, ncclProfilerCallback_t profFunction);
+  // Return the number of adapters.
+  ncclResult_t (*devices)(int* ndev);
+  // Get various device properties.
+  ncclResult_t (*getProperties)(int dev, ncclNetProperties_v10_t* props);
+  // Create a receiving object and provide a handle to connect to it. The
+  // handle can be up to NCCL_NET_HANDLE_MAXSIZE bytes and will be exchanged
+  // between ranks to create a connection.
+  ncclResult_t (*listen)(int dev, void* handle, void** listenComm);
+  // Connect to a handle and return a sending comm object for that peer.
+  // This call must not block for the connection to be established, and instead
+  // should return successfully with sendComm == NULL with the expectation that
+  // it will be called again until sendComm != NULL.
+  // If *sendDevComm points to a valid object, then NCCL is requesting device offload for this connection
+  ncclResult_t (*connect)(int dev, ncclNetCommConfig_v10_t* config, void* handle, void** sendComm, ncclNetDeviceHandle_v10_t** sendDevComm);
+  // Finalize connection establishment after remote peer has called connect.
+  // This call must not block for the connection to be established, and instead
+  // should return successfully with recvComm == NULL with the expectation that
+  // it will be called again until recvComm != NULL.
+  // If *recvDevComm points to a valid object, then NCCL is requesting device offload for this connection
+  ncclResult_t (*accept)(void* listenComm, void** recvComm, ncclNetDeviceHandle_v10_t** recvDevComm);
+  // Register/Deregister memory. Comm can be either a sendComm or a recvComm.
+  // Type is either NCCL_PTR_HOST or NCCL_PTR_CUDA.
+  ncclResult_t (*regMr)(void* comm, void* data, size_t size, int type, void** mhandle);
+  /* DMA-BUF support */
+  ncclResult_t (*regMrDmaBuf)(void* comm, void* data, size_t size, int type, uint64_t offset, int fd, void** mhandle);
+  ncclResult_t (*deregMr)(void* comm, void* mhandle);
+  // Asynchronous send to a peer.
+  // May return request == NULL if the call cannot be performed (or would block)
+  ncclResult_t (*isend)(void* sendComm, void* data, size_t size, int tag, void* mhandle, void* phandle, void** request);
+  // Asynchronous recv from a peer.
+  // May return request == NULL if the call cannot be performed (or would block)
+  ncclResult_t (*irecv)(void* recvComm, int n, void** data, size_t* sizes, int* tags, void** mhandles, void** phandles, void** request);
+  // Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
+  // visible to the GPU
+  ncclResult_t (*iflush)(void* recvComm, int n, void** data, int* sizes, void** mhandles, void** request);
+  // Test whether a request is complete. If size is not NULL, it returns the
+  // number of bytes sent/received.
+  ncclResult_t (*test)(void* request, int* done, int* sizes);
+  // Close and free send/recv comm objects
+  ncclResult_t (*closeSend)(void* sendComm);
+  ncclResult_t (*closeRecv)(void* recvComm);
+  ncclResult_t (*closeListen)(void* listenComm);
+
+  // Copy the given mhandle to a dptr in a format usable by this plugin's device code
+  ncclResult_t (*getDeviceMr)(void* comm, void* mhandle, void** dptr_mhandle);
+
+  // Notify the plugin that a recv has completed by the device
+  ncclResult_t (*irecvConsumed)(void* recvComm, int n, void* request);
+
+  // Virtual NIC APIs. makeVDevice will create a virtual NIC given the specified properties, and tell the caller
+  // what index this new vNIC exists at
+  ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_v10_t* props);
+} ncclNet_v10_t;
+
+#endif // end include guard

projects/rccl/ext-net/example/nccl/net_v2.h

@@ -2,8 +2,8 @@
  * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
  */
 
-#ifndef NCCL_NET_V2_H_
-#define NCCL_NET_V2_H_
+#ifndef NET_V2_H_
+#define NET_V2_H_
 
 typedef struct {
   // Name of the network (mainly for logs)

projects/rccl/ext-net/example/nccl/net_v3.h

@@ -2,8 +2,8 @@
  * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
  */
 
-#ifndef NCCL_NET_V3_H_
-#define NCCL_NET_V3_H_
+#ifndef NET_V3_H_
+#define NET_V3_H_
 
 #define NCCL_NET_MAX_REQUESTS_V3 16
 

projects/rccl/ext-net/example/nccl/net_v4.h

@@ -2,8 +2,8 @@
  * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
  */
 
-#ifndef NCCL_NET_V4_H_
-#define NCCL_NET_V4_H_
+#ifndef NET_V4_H_
+#define NET_V4_H_
 
 #define NCCL_NET_HANDLE_MAXSIZE_V4 64
 

projects/rccl/ext-net/example/nccl/net_v5.h

@@ -2,8 +2,8 @@
  * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
  */
 
-#ifndef NCCL_NET_V5_H_
-#define NCCL_NET_V5_H_
+#ifndef NET_V5_H_
+#define NET_V5_H_
 
 typedef ncclNetProperties_v6_t ncclNetProperties_v5_t;
 typedef struct {

projects/rccl/ext-net/example/nccl/net_v6.h

@@ -2,10 +2,8 @@
  * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
  */
 
-#ifndef NCCL_NET_V6_H_
-#define NCCL_NET_V6_H_
-
-#define NCCL_NET_MAX_REQUESTS_V6 8
+#ifndef NET_V6_H_
+#define NET_V6_H_
 
 typedef struct {
   char* name;     // Used mostly for logging.

projects/rccl/ext-net/example/nccl/net_v7.h

@@ -2,10 +2,8 @@
  * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
  */
 
-#ifndef NCCL_NET_V7_H_
-#define NCCL_NET_V7_H_
-
-#include "net_device.h"
+#ifndef NET_V7_H_
+#define NET_V7_H_
 
 typedef struct {
   char* name;                      // Used mostly for logging.

projects/rccl/ext-net/example/nccl/net_v8.h

@@ -2,10 +2,8 @@
  * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
  */
 
-#ifndef NCCL_NET_V8_H_
-#define NCCL_NET_V8_H_
-
-#include "net_device.h"
+#ifndef NET_V8_H_
+#define NET_V8_H_
 
 typedef struct {
   char* name;                      // Used mostly for logging.

projects/rccl/ext-net/example/nccl/net_v9.h

@@ -2,18 +2,14 @@
  * Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
  */
 
-#ifndef NCCL_NET_V9_H_
-#define NCCL_NET_V9_H_
-
-#include "net_device.h"
+#ifndef NET_V9_H_
+#define NET_V9_H_
 
 #define NCCL_NET_MAX_DEVS_PER_NIC_V9 4
-#define NCCL_NET_MAX_DEVS_PER_NIC NCCL_NET_MAX_DEVS_PER_NIC_V9
 typedef struct {
   int ndevs;
   int devs[NCCL_NET_MAX_DEVS_PER_NIC_V9];
 } ncclNetVDeviceProps_v9_t;
-typedef ncclNetVDeviceProps_v9_t ncclNetVDeviceProps_t;
 
 typedef struct {
   char* name;                      // Used mostly for logging.
@@ -35,8 +31,6 @@ typedef struct {
   size_t maxCollBytes;             // Max transfer size for collective operations
 } ncclNetProperties_v9_t;
 
-typedef ncclNetProperties_v9_t ncclNetProperties_t;
-
 typedef struct {
   // Name of the network (mainly for logs)
   const char* name;
@@ -93,7 +87,7 @@ typedef struct {
 
   // Virtual NIC APIs. makeVDevice will create a virtual NIC given the specified properties, and tell the caller
   // what index this new vNIC exists at
-  ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_t* props);
+  ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_v9_t* props);
 } ncclNet_v9_t;
 
 #endif // end include guard

projects/rccl/ext-net/example/plugin.c

@@ -11,7 +11,7 @@
 
 int max_requests = NCCL_NET_MAX_REQUESTS;
 
-__hidden ncclResult_t pluginInit(ncclDebugLogger_t logFunction) { return ncclSuccess; }
+__hidden ncclResult_t pluginInit(ncclDebugLogger_t logFunction, ncclProfilerCallback_t profFunction) { return ncclSuccess; }
 __hidden ncclResult_t pluginDevices(int* ndev) { *ndev = 0; return ncclSuccess; }
 __hidden ncclResult_t pluginPciPath(int dev, char** path) { return ncclInternalError; }
 __hidden ncclResult_t pluginPtrSupport(int dev, int* supportedTypes) { return ncclInternalError; }
@@ -52,13 +52,13 @@ __hidden ncclResult_t pluginGetProperties(int dev, ncclNetProperties_t* props) {
 }
 
 __hidden ncclResult_t pluginListen(int dev, void* handle, void** listenComm) { return ncclInternalError; }
-__hidden ncclResult_t pluginConnect(int dev, void* handle, void** sendComm, ncclNetDeviceHandle_t** sendDevComm) { return ncclInternalError; }
+__hidden ncclResult_t pluginConnect(int dev, ncclNetCommConfig_t* config, void* handle, void** sendComm, ncclNetDeviceHandle_t** sendDevComm) { return ncclInternalError; }
 __hidden ncclResult_t pluginAccept(void* listenComm, void** recvComm, ncclNetDeviceHandle_t** recvDevComm) { return ncclInternalError; }
 __hidden ncclResult_t pluginRegMr(void* collComm, void* data, size_t size, int type, void** mhandle) { return ncclInternalError; }
 __hidden ncclResult_t pluginRegMrDmaBuf(void* collComm, void* data, size_t size, int type, uint64_t offset, int fd, void** mhandle) { return ncclInternalError; }
 __hidden ncclResult_t pluginDeregMr(void* collComm, void* mhandle) { return ncclInternalError;}
-__hidden ncclResult_t pluginIsend(void* sendComm, void* data, size_t size, int tag, void* mhandle, void** request) { return ncclInternalError; }
-__hidden ncclResult_t pluginIrecv(void* recvComm, int n, void** data, size_t* sizes, int* tags, void** mhandles, void** request) { return ncclInternalError; }
+__hidden ncclResult_t pluginIsend(void* sendComm, void* data, size_t size, int tag, void* mhandle, void* phandle, void** request) { return ncclInternalError; }
+__hidden ncclResult_t pluginIrecv(void* recvComm, int n, void** data, size_t* sizes, int* tags, void** mhandles, void** phandles, void** request) { return ncclInternalError; }
 __hidden ncclResult_t pluginIflush(void* recvComm, int n, void** data, int* sizes, void** mhandles, void** request) { return ncclInternalError; }
 __hidden ncclResult_t pluginTest(void* request, int* done, int* size) { return ncclInternalError; }
 __hidden ncclResult_t pluginCloseSend(void* sendComm) { return ncclInternalError; }
@@ -70,7 +70,7 @@ __hidden ncclResult_t pluginMakeVDevice(int* d, ncclNetVDeviceProps_t* props) {
 
 #define PLUGIN_NAME "Plugin"
 
-ncclNet_v9_t ncclNetPlugin_v9 = {
+const ncclNet_v10_t ncclNetPlugin_v10 = {
   .name = PLUGIN_NAME,
   .init = pluginInit,
   .devices = pluginDevices,
@@ -93,6 +93,51 @@ ncclNet_v9_t ncclNetPlugin_v9 = {
   .makeVDevice   = pluginMakeVDevice,
 };
 
+__hidden ncclResult_t pluginInit_v9(ncclDebugLogger_t logFunction) {
+  return pluginInit(logFunction, NULL);
+}
+
+__hidden ncclResult_t pluginGetProperties_v9(int dev, ncclNetProperties_v9_t* props) {
+  return pluginGetProperties(dev, (ncclNetProperties_t*)props);
+}
+
+__hidden ncclResult_t pluginConnect_v9(int dev, void* handle, void** sendComm, ncclNetDeviceHandle_t** sendDevComm){
+  return pluginConnect(dev, NULL, handle, sendComm, sendDevComm);
+}
+
+__hidden ncclResult_t pluginIsend_v9(void* sendComm, void* data, size_t size, int tag, void* mhandle, void** request) {
+  return pluginIsend(sendComm, data, size, tag, mhandle, NULL, request);
+}
+
+__hidden ncclResult_t pluginIrecv_v9(void* recvComm, int n, void** data, size_t* sizes, int* tags, void** mhandles, void** request) {
+  return pluginIrecv(recvComm, n, data, sizes, tags, mhandles, NULL, request);
+}
+
+__hidden ncclResult_t pluginMakeVDevice_v9(int* d, ncclNetVDeviceProps_v9_t* props) { return ncclInternalError; }
+
+const ncclNet_v9_t ncclNetPlugin_v9 = {
+  .name = PLUGIN_NAME,
+  .init = pluginInit_v9,
+  .devices = pluginDevices,
+  .getProperties = pluginGetProperties_v9,
+  .listen = pluginListen,
+  .connect = pluginConnect_v9,
+  .accept = pluginAccept,
+  .regMr = pluginRegMr,
+  .regMrDmaBuf = pluginRegMrDmaBuf,
+  .deregMr = pluginDeregMr,
+  .isend = pluginIsend_v9,
+  .irecv = pluginIrecv_v9,
+  .iflush = pluginIflush,
+  .test = pluginTest,
+  .closeSend = pluginCloseSend,
+  .closeRecv = pluginCloseRecv,
+  .closeListen = pluginCloseListen,
+  .getDeviceMr = pluginGetDeviceMr,
+  .irecvConsumed = pluginIrecvConsumed,
+  .makeVDevice   = pluginMakeVDevice_v9,
+};
+
 __hidden ncclResult_t pluginGetProperties_v8(int dev, ncclNetProperties_v8_t* props_v8) {
   ncclNetProperties_t props;
   ncclResult_t ret = pluginGetProperties(dev, &props);
@@ -113,22 +158,22 @@ __hidden ncclResult_t pluginGetProperties_v8(int dev, ncclNetProperties_v8_t* pr
 }
 
 __hidden ncclResult_t pluginIsend_v8(void* sendComm, void* data, int size, int tag, void* mhandle, void** request) {
-  return pluginIsend(sendComm, data, (int)size, tag, mhandle, request);
+  return pluginIsend(sendComm, data, (int)size, tag, mhandle, NULL, request);
 }
 
 __hidden ncclResult_t pluginIrecv_v8(void* recvComm, int n, void** data, int* sizes, int* tags, void** mhandles, void** request) {
   size_t sizesOut[NCCL_PLUGIN_MAX_RECVS];
   for (int i=0; i<n; i++) sizesOut[i] = sizes[i];
-  return pluginIrecv(recvComm, 1, data, sizesOut, tags, mhandles, request);
+  return pluginIrecv(recvComm, 1, data, sizesOut, tags, mhandles, NULL, request);
 }
 
 const ncclNet_v8_t ncclNetPlugin_v8 = {
   .name = PLUGIN_NAME,
-  .init = pluginInit,
+  .init = pluginInit_v9,
   .devices = pluginDevices,
   .getProperties = pluginGetProperties_v8,
   .listen = pluginListen,
-  .connect = pluginConnect,
+  .connect = pluginConnect_v9,
   .accept = pluginAccept,
   .regMr = pluginRegMr,
   .regMrDmaBuf = pluginRegMrDmaBuf,
@@ -168,11 +213,11 @@ __hidden ncclResult_t pluginRegMr_v7(void* collComm, void* data, int size, int t
 
 const ncclNet_v7_t ncclNetPlugin_v7 = {
   .name = PLUGIN_NAME,
-  .init = pluginInit,
+  .init = pluginInit_v9,
   .devices = pluginDevices,
   .getProperties = pluginGetProperties_v7,
   .listen = pluginListen,
-  .connect = pluginConnect,
+  .connect = pluginConnect_v9,
   .accept = pluginAccept,
   .regMr = pluginRegMr_v7,
   .regMrDmaBuf = pluginRegMrDmaBuf,
@@ -209,7 +254,7 @@ __hidden ncclResult_t pluginAccept_v6(void* listenComm, void** recvComm) { retur
 
 const ncclNet_v6_t ncclNetPlugin_v6 = {
   .name = PLUGIN_NAME,
-  .init = pluginInit,
+  .init = pluginInit_v9,
   .devices = pluginDevices,
   .getProperties = pluginGetProperties_v6,
   .listen = pluginListen,
@@ -230,7 +275,7 @@ const ncclNet_v6_t ncclNetPlugin_v6 = {
 /* v5 Compat */
 const ncclNet_v5_t ncclNetPlugin_v5 = {
   .name = PLUGIN_NAME,
-  .init = pluginInit,
+  .init = pluginInit_v9,
   .devices = pluginDevices,
   .getProperties = pluginGetProperties_v6,
   .listen = pluginListen,
@@ -275,7 +320,7 @@ static ncclResult_t pluginConnect_v4(int dev, void* handle, void** sendComm) {
   ncclResult_t ret;
   do {
     ncclNetDeviceHandle_v7_t* handle = NULL;
-    ret = pluginConnect(dev, handle, sendComm, &handle);
+    ret = pluginConnect(dev, NULL, handle, sendComm, &handle);
   } while (ret == ncclSuccess && *sendComm == NULL);
   return ret;
 }
@@ -289,7 +334,7 @@ static ncclResult_t pluginAccept_v4(void* listenComm, void** recvComm) {
 }
 const ncclNet_v4_t ncclNetPlugin_v4 = {
   .name = PLUGIN_NAME,
-  .init = pluginInit,
+  .init = pluginInit_v9,
   .devices = pluginDevices,
   .getProperties = pluginGetProperties_v4,
   .listen = pluginListen,
@@ -318,7 +363,7 @@ static ncclResult_t pluginFlush(void* recvComm, void* data, int size, void* mhan
 }
 static ncclResult_t pluginInit_v3(ncclDebugLogger_t logFunction) {
   max_requests = NCCL_NET_MAX_REQUESTS_V3;
-  return pluginInit(logFunction);
+  return pluginInit(logFunction, NULL);
 }
 #include <string.h>
 static ncclResult_t pluginListen_v3(int dev, void* handle, void** listenComm) {