BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
Paper
•
2402.04291
•
Published
•
48
Quantization | Compression
-
-
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Paper • 2401.18079 • Published • 7 -
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
Paper • 2402.08958 • Published • 3 -
OneBit: Towards Extremely Low-bit Large Language Models
Paper • 2402.11295 • Published • 22 -
Genie: Generative Interactive Environments
Paper • 2402.15391 • Published • 70