diff --git a/include/Makefile.am b/include/Makefile.am
index 687a16e9f..3262d2c8d 100644
--- a/include/Makefile.am
+++ b/include/Makefile.am
@@ -27,6 +27,7 @@ noinst_HEADERS = \
 	nccl_ofi_ofiutils.h \
 	nccl_ofi_tracepoint.h \
 	tracing_impl/lttng.h \
+	tracing_impl/nvtx.h \
 	nccl-headers/net.h \
 	nccl-headers/error.h \
 	nccl-headers/nvidia/err.h \
diff --git a/include/nccl_ofi_tracepoint.h b/include/nccl_ofi_tracepoint.h
index 17f569cab..511354c98 100644
--- a/include/nccl_ofi_tracepoint.h
+++ b/include/nccl_ofi_tracepoint.h
@@ -6,55 +6,69 @@
 #pragma once
 
 #include "config.h"
+#include "tracing_impl/nvtx.h"
 #include "tracing_impl/lttng.h"
 
 #define NCCL_OFI_TRACE_SEND(dev, size, comm, msg_seq_num, request, nccl_req) do { \
 	lttng_ust_tracepoint(nccl_ofi_plugin, Send, dev, size, comm, msg_seq_num, request, nccl_req); \
+	nvtx_push("Send"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_SEND_CTRL_RECV(dev, rail_id, comm, msg_seq_num) do { \
 		lttng_ust_tracepoint(nccl_ofi_plugin, Send_ctrl_recv, dev, rail_id, comm, msg_seq_num); \
+		nvtx_push("Send_ctrl_recv"); \
 	} while (0)
 
 #define NCCL_OFI_TRACE_SEND_WRITE_SEG_START(dev, rail_id, size, comm, msg_seq_num, request) do { \
 		lttng_ust_tracepoint(nccl_ofi_plugin, Send_write_segment_start, dev, rail_id, size, comm, msg_seq_num, request); \
+		nvtx_push("Send_write_segment_start"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_SEND_WRITE_SEG_COMPLETE(dev, rail_id, comm, msg_seq_num, request) do { \
 	lttng_ust_tracepoint(nccl_ofi_plugin, Send_write_segment_complete, dev, rail_id, comm, msg_seq_num, request); \
+	nvtx_push("Send_write_segment_complete");                           \
 	} while(0)
 
 #define NCCL_OFI_TRACE_RECV(dev, tag, size, request, nccl_req) do { \
 	lttng_ust_tracepoint(nccl_ofi_plugin, Recv, dev, tag, size, request, nccl_req); \
+	nvtx_push("Recv"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_RECV_CTRL_SEND_COMPLETE(request) do { \
 		lttng_ust_tracepoint(nccl_ofi_plugin, Recv_ctrl_send_complete, request); \
+		nvtx_push("Recv_ctrl_send_complete"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_RECV_SEGMENT_COMPLETE(dev, rail_id, size, request) do { \
 	lttng_ust_tracepoint(nccl_ofi_plugin, Recv_segment_complete, dev, rail_id, size, request); \
+	nvtx_push("Recv_segment_complete"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_EAGER_RECV(dev, rail_id, comm, msg_seq_num) do { \
 		lttng_ust_tracepoint(nccl_ofi_plugin, Eager_recv, dev, rail_id, comm, msg_seq_num); \
+		nvtx_push("Eager_recv"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_COMPLETIONS(request,ctx) do { \
 	lttng_ust_tracepoint(nccl_ofi_plugin, ProcessCompletions, request,ctx); \
+	nvtx_push("ProcessCompletions"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_FLUSH(request, nccl_req) do { \
 	lttng_ust_tracepoint(nccl_ofi_plugin, Flush, request, nccl_req); \
+	nvtx_push("Flush"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_PENDING_INSERT(request) do { \
 	lttng_ust_tracepoint(nccl_ofi_plugin, Pending_queue_insert, request); \
+	nvtx_push("Pending_queue_insert"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_PENDING_REMOVE(request) do { \
 	lttng_ust_tracepoint(nccl_ofi_plugin, Pending_queue_remove, request); \
+	nvtx_push("Pending_queue_remove"); \
 	} while(0)
 
 #define NCCL_OFI_TRACE_POP(...) do { \
+		nvtx_pop(); \
 	} while(0)
diff --git a/include/tracing_impl/nvtx.h b/include/tracing_impl/nvtx.h
new file mode 100644
index 000000000..5f8680bec
--- /dev/null
+++ b/include/tracing_impl/nvtx.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (c) 2022-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
+ */
+
+#pragma once
+#if HAVE_NVTX_TRACING
+#include "nvToolsExt.h"
+static inline void nvtx_push(const char* name) {
+	const nvtxEventAttributes_t eventAttrib = {
+		.version = NVTX_VERSION,
+		.size = NVTX_EVENT_ATTRIB_STRUCT_SIZE,
+		.colorType = NVTX_COLOR_ARGB,
+		.color = 0xeb9234,
+		.messageType = NVTX_MESSAGE_TYPE_ASCII,
+		.message = { .ascii = name },
+	};
+	nvtxRangePushEx(&eventAttrib);
+}
+static inline void nvtx_pop(void) {
+	nvtxRangePop();
+}
+#else
+static inline void nvtx_push(const char* name){ (void)name; }
+static inline void nvtx_pop(void){}
+#endif