Skip to main content

LLM Inference

Explore machine learning papers and reviews related to LLM Inference. Find insights, analysis, and implementation details.

  • Tagged with
  • 5 papers
Back to all papers

Papers Related to LLM Inference

OSDI 2026

MPK: A Compiler and Runtime for Mega-Kernelizing Tensor Programs

Xinhao Cheng, Zhihao Zhang, +19

Follow how MPK turns a model into one persistent GPU kernel by tracking dependencies between tasks on individual SMs, with a task-graph explorer, a cross-task pipelining timeline, and a runnable CPU model of its compiler stages.

arXiv 2025

Collective Communication for 100k+ GPUs

Min Si, Pavan Balaji, +37

NCCLX is Meta's communication stack for Llama 4: host-driven, zero-copy collectives that start a 96K-GPU job 11x faster and cut decode time by up to 83%.

arXiv 2026

Every µs Matters: Achieving Near Speed-of-Light Latency in GPU Collectives

Siyuan Shen, Anton Korzh, +11

How the Every µs Matters paper brings small GPU AllReduce operations close to the hardware speed-of-light bound: it measures a 1.404 µs floor on GB200, removes memory barriers with LL, sentinel and LL128 atomic signalling, and cuts vLLM inter-token latency by up to 13%.

OSDI 2025

NanoFlow: Towards Optimal Large Language Model Serving Throughput

Kan Zhu, Yufei Gao, +14

How NanoFlow raises LLM serving throughput by overlapping compute, memory and network work inside a single GPU: it shows serving is compute-bound, splits each batch into nano-batches, and shares SMs between concurrent kernels, reaching 1.91x the throughput of TensorRT-LLM.

SOSP 2023

vLLM / PagedAttention

Efficient Memory Management for Large Language Model Serving with PagedAttention

Woosuk Kwon, Zhuohan Li, +7

How PagedAttention (the memory manager behind vLLM) applies OS-style virtual-memory paging to the KV cache — fixed-size blocks, a block table, and copy-on-write prefix sharing — to reduce final-block waste, remove external block fragmentation, and improve throughput in the paper’s measured serving workloads.

Mastodon