Link 4.0 release notes to AMQP benchmark blog post

(cherry picked from commit bd24b07)

Author: ansd

release-notes/4.0.0.md

@@ -10,7 +10,7 @@ Some key improvements in this release are listed below.
 
  * [Khepri](https://www.youtube.com/watch?v=whVqpgvep90), an [alternative schema data store](https://github.com/rabbitmq/rabbitmq-server/pull/7206) developed to replace Mnesia, has matured
  * [AMQP 1.0 is now a core protocol](https://www.rabbitmq.com/blog/2024/08/05/native-amqp) that is always enabled. Its plugin is now a no-op that only exists to simplify upgrades.
- * The AMQP 1.0 implementation is now significantly more efficient: its peak throughput is [more than double than that of 3.13.x](https://github.com/rabbitmq/rabbitmq-server/pull/9022)
+ * The AMQP 1.0 implementation is now significantly more efficient: its peak throughput is [more than double than that of 3.13.x](https://www.rabbitmq.com/blog/2024/08/21/amqp-benchmarks)
    on some workloads
  * Efficient sub-linear [quorum queue recovery on node startup using checkpoints](https://github.com/rabbitmq/rabbitmq-server/pull/10637)
  * Quorum queues now [support priorities](https://github.com/rabbitmq/rabbitmq-server/pull/10637) (but not exactly the same way as classic queues)
@@ -238,7 +238,7 @@ This section is incomplete and will be expanded as 4.0 approaches its release ca
 
    GitHub issues: [#9022](https://github.com/rabbitmq/rabbitmq-server/pull/9022), [#10662](https://github.com/rabbitmq/rabbitmq-server/pull/10662)
 
- * The AMQP 1.0 implementation is now significantly more efficient: its peak throughput is more than double than that of 3.13.x
+ * The AMQP 1.0 implementation is now significantly more efficient: its peak throughput is [more than double than that of 3.13.x](https://www.rabbitmq.com/blog/2024/08/21/amqp-benchmarks)
    on some workloads.
 
    GitHub issue: [#9022](https://github.com/rabbitmq/rabbitmq-server/pull/9022)