ResidualQuant: KV Cache Quantization for Looped Transformers with 2-Bit Residuals
Paper • 2610.10381 • Published • 9
heejunkim
hjkim00
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
ResidualQuant: KV Cache Quantization for Looped Transformers with 2-Bit Residuals authored a paper about 1 month ago
From Noise to Diversity: Random Embedding Injection in LLM Reasoning authored a paper about 1 month ago
ResidualQuant: KV Cache Quantization for Looped Transformers with 2-Bit ResidualsOrganizations
