paper-with-me

홈 › Papers

Context Parallelism for Scalable Million-Token Inference

2024-11-04 · Amy Yang, Jingyi Yang, Aya Ibrahim, Xinfeng Xie, Bangsheng Tang, Grigory Sizov, Jeremy Reizenstein, Jongsoo Park, Jianyu Huang

We present context parallelism for long-context large language model inference, which achieves near-linear scaling for long-context prefill latency with up to 128 H100 GPUs across 16 nodes. Particularly, our method achieves 1M context prefill with Llama3 405B model in 77s (93% parallelization efficiency, 63% FLOPS utilization) and 128K context prefill in 3.8s. We develop two lossless exact ring attention variants: pass-KV and pass-Q to cover a wide range of use cases with the state-of-the-art performance: full prefill, persistent KV prefill and decode. Benchmarks on H100 GPU hosts inter-connected with RDMA and TCP both show similar scalability for long-context prefill, demonstrating that our method scales well using common commercial data center with medium-to-low inter-host bandwidth.

📄 PDF Abstract BibTeX arXiv:2411.01783

Code (0)

등록된 구현이 없습니다.

Tasks

GPULanguage ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Medha: Efficiently Serving Multi-Million Context Length LLM Inference Requests Without Approximations

2024-09-25 · Amey Agrawal, Haoran Qiu, Junda Chen, Íñigo Goiri 외

As large language models (LLMs) handle increasingly longer contexts, serving long inference requests of millions of tokens presents unique challenges. We show that existing work for long context inference is largely base…

BlockingChunkingScheduling

Helix Parallelism: Rethinking Sharding Strategies for Interactive Multi-Million-Token LLM Decoding

2025-07-07 · Nidhi Bhatia, Ankit More, Ritika Borkar, Tiyasa Mitra 외 arxiv

As LLMs scale to multi-million-token KV histories, real-time autoregressive decoding under tight Token-to-Token Latency (TTL) constraints faces growing pressure. Two core bottlenecks dominate: accessing Feed-Forward Netw…

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

2024-08-19 · Yukang Chen, Fuzhao Xue, Dacheng Li, Qinghao Hu 외

Long-context capability is critical for multi-modal foundation models, especially for long video understanding. We introduce LongVILA, a full-stack solution for long-context visual-language models by co-designing the alg…

Video CaptioningVideo Question AnsweringVideo Understanding

Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits

2025-10-31 · Dowon Kim, MinJae Lee, Janghyeon Kim, HyuckSung Kwon 외 arxiv

The expansion of context windows in large language models (LLMs) to multi-million tokens introduces severe memory and compute bottlenecks, particularly in managing the growing Key-Value (KV) cache. While Compute Express …

PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory

2026-08-04 · Dawei Liu, Haixu Song, Shuang Cheng, Shijie Wang 외 arxiv

Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: sequential chunk-wise updates can overwrite early critical evidence with…

Multi-hop Question AnsweringReinforcement Learning