4 papers
High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration
Gradwell Dzikanyanga, Yanqi Pan, Weihao Yang +3
Long-context large language model inference relies on the KV cache to avoid redundant attention computation, but incurs high memory and bandwidth overheads. Low-bit KV-cache quanti…
TTKV: Temporal-Tiered KV Cache for Long-Context LLM Inference
Gradwell Dzikanyanga, Weihao Yang, Hao Huang +4
Key-value (KV) caching is critical for efficient inference in large language models (LLMs), yet its memory footprint scales linearly with context length, resulting in a severe scal…
Memory as Asset: From Agent-centric to Human-centric Memory Management
Yanqi Pan, Qinghao Huang, Weihao Yang
We proudly introduce Memory-as-Asset, a new memory paradigm towards human-centric artificial general intelligence (AGI). In this paper, we formally emphasize that human-centric, pe…
HybridEP: Scaling Expert Parallelism to Cross-Datacenter Scenario via Hybrid Expert/Data Transmission
Weihao Yang, Hao Huang, Donglei Wu +6
Mixture-of-Experts (MoE) has become a popular architecture for scaling large models. However, the rapidly growing scale outpaces model training on a single DC, driving a shift towa…