-
SAM-Decoding Public
Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
-
-
LoRS Public
Official Implementation of LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model
Python UpdatedJan 22, 2025 -
ktransformers Public
Forked from kvcache-ai/ktransformersA Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Python Apache License 2.0 UpdatedAug 28, 2024 -
-