minor: add acknowledgement (#208)

* minor: update acknowledgement

* upd

Author: zhyncs

blog/2025-09-25-gb200-part-2.md

@@ -72,3 +72,7 @@ Though our implementation has demonstrated significant performance boosts, there
 * **Kernel Optimizations**: There is still room for improvements for some kernels to fully utilize the hardware.
 * **More Models**: Other powerful models, either existing or to be released, will also be optimized, such as Kimi-K2, Qwen, and GLM 4.5.
 * **OME for Easier Usage**: OME is a Kubernetes operator for enterprise-grade management and serving of LLMs, which simplifies the deployment and operations of the model.
+
+## Acknowledgement
+
+The GB200 optimizations would not have been possible without the collective efforts of the SGLang community. Special thanks to the SGLang team, FlashInfer team, Mooncake team, NVIDIA DevTech team, NVIDIA Enterprise Product team, NVIDIA DGX Cloud team, and the Dynamo team for driving this forward together! And we’ll continue pushing performance optimizations and actively working on adapting SGLang to upcoming hardware platforms, so the community can benefit from every new generation of acceleration.