2 papers
cs.AI2026
Beneath the Tokens: A Performance Engineering Study of Multi-Token Prediction in GPU-Accelerated LLM Inference
Suwesh Prasad Sah
Autoregressive large language model inference repeatedly invokes the target model to generate one token at a time, making generation sensitive to GPU memory movement and sequential…
cs.CV2024
Parallel Neural Computing for Scene Understanding from LiDAR Perception in Autonomous Racing
Suwesh Prasad Sah
Autonomous driving in high-speed racing, as opposed to urban environments, presents significant challenges in scene understanding due to rapid changes in the track environment. Tra…