S-LoRA: Serving Thousands of Concurrent LoRA Adapters Paper β’ 2311.03285 β’ Published Nov 6, 2023 β’ 28
Towards Modular LLMs by Building and Reusing a Library of LoRAs Paper β’ 2405.11157 β’ Published May 18, 2024 β’ 27
Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning Paper β’ 2407.15762 β’ Published Jul 22, 2024 β’ 10
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization Paper β’ 2401.18079 β’ Published Jan 31, 2024 β’ 7 β’ 2