Skip to content
Papers.

Inference and efficiency

Serving, attention kernels, KV caches, quantisation: the cost of running models. 4 papers from 4 labs.

4 of 4 papers, newest first

PaperCitations
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache CompressionA 552B mixture-of-experts model with a 1M-token context, built to shrink the KV cache for agent workloads.DeepSeek · Sep 20267
SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model TransformationSwiftKV lets prompt tokens skip later layers and merges KV caches, cutting prefill cost for long-prompt workloads.Snowflake · Oct 202418
Efficient Memory Management for Large Language Model Serving with PagedAttentionvLLM manages the KV cache like pages of virtual memory, serving models with 2 to 4 times the throughput.UC Berkeley · Sep 20238,469
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessFlashAttention computes exact attention with far fewer GPU memory reads and writes, making long sequences faster.Stanford University · May 20225,331

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.