Michael W. Mahoney

发表论文 23 篇 · 总被引 1321 次 · h-index 10

代表论文

• 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)
• An LLM Compiler for Parallel Function Calling (2023 · International Conference on Machine Learning · 被引 204)
• LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement (2024 · Annual Meeting of the Association for Computational Linguistics · 被引 91)
• Squeezed Attention: Accelerating Long Context Length LLM Inference (2024 · Annual Meeting of the Association for Computational Linguistics · 被引 58)
• Towards Scalable and Versatile Weight Space Learning (2024 · International Conference on Machine Learning · 被引 46)