Update 2025-07-25-spec-forge.md (#178)

Author: zhyncs

blog/2025-07-25-spec-forge.md

@@ -89,6 +89,6 @@ We would like to express our heartfelt gratitude to the following teams and coll
 
 We are especially grateful to Meituan for their early support and contributions to this project. We also extend our sincere thanks to [Voltage Park](https://www.voltagepark.com/), our official infrastructure partner, whose formal collaboration with the SGLang team provided the compute foundation behind SpecForge. Their support enabled us to train and evaluate large-scale speculative decoding models efficiently and reliably, and we deeply appreciate their commitment to democratizing cutting-edge AI infrastructure.
 
-“Our mission at Voltage Park is to be a catalyst for innovation by democratizing access to high-performance AI infrastructure. A thriving AI research ecosystem is one where the tools to innovate are shaped by many voices and not concentrated in the hands of a few," said Saurabh Giri, Chief Product and Technology Officer at Voltage Park." This is why we are so proud to support the SGLang team with the critical infrastructure to develop high-quality, open-source projects like SpecForge -- we believe that foundational open-source models and frameworks should be for the public good and are essential for progress. We look forward to amazing applications from the community with these new capabilities.”
+“**Our mission at Voltage Park is to be a catalyst for innovation by democratizing access to high-performance AI infrastructure. A thriving AI research ecosystem is one where the tools to innovate are shaped by many voices and not concentrated in the hands of a few,**" said Saurabh Giri, Chief Product and Technology Officer at Voltage Park. "**This is why we are so proud to support the SGLang team with the critical infrastructure to develop high-quality, open-source projects like SpecForge -- we believe that foundational open-source models and frameworks should be for the public good and are essential for progress. We look forward to amazing applications from the community with these new capabilities.**”
 
 We're excited to see what the community will create with SpecForge. Whether you're optimizing existing models or training new ones, your feedback, contributions, and collaborations are all welcome—let’s accelerate open-source LLM innovation together!