A. Gholami

发表论文 84 篇 · 总被引 11647 次 · h-index 44

代表论文

• A Survey of Quantization Methods for Efficient Neural Network Inference (2021 · Low-Power Computer Vision · 被引 1701)
• Characterizing possible failure modes in physics-informed neural networks (2021 · Neural Information Processing Systems · 被引 1327)
• KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization (2024 · Neural Information Processing Systems · 被引 673)
• AI and Memory Wall (2024 · IEEE Micro · 被引 413)
• SqueezeLLM: Dense-and-Sparse Quantization (2023 · International Conference on Machine Learning · 被引 365)
• A Fast Post-Training Pruning Framework for Transformers (2022 · Neural Information Processing Systems · 被引 242)