Search papers, labs, and topics across Lattice.
2
3
5
3
The DeepSeek-V4.1-Flash model, a multimodal Mixture-of-Experts model with 552B backbone parameters and support for contexts of up to one million tokens, is introduced, substantially improving cost efficiency for agentic workloads and pushing the limits of KV cache compression.
Lossy verification in Speculative Decoding can accelerate inference but risks severe degradation in output quality if not carefully managed.
