TensorRT-LLM Livestream: DeepSeek R1 performance optimization to push the throughput performance boundary

Learn how we push the boundary to get the world fastest GPU inferences on DeepSeek R1 based on NVIDIA blackwell architecture in tomorrow’s developer livestream.
Join the livestream on the NVIDIA Developer YouTube channel https://www.youtube.com/watch?v=5ftMMBj6xj0&ab_channel=NVIDIADeveloper. Add to calendar AddEvent