Related papers: P/D-Serve: Serving Disaggregated Large Language Mo…

Modern LLM serving systems must sustain high throughput while meeting strict latency SLOs across two distinct inference phases: compute-intensive prefill and memory-bound decode phases. Existing approaches either (1) aggregate both phases…

Fine-tuning a large language model (LLM) using the local data of edge users can enable personalized services and applications. For privacy protection, the prevalent solution adopts distributed learning for fine-tuning and integrates…

Sparse large language models (LLMs) with Mixture of Experts (MoE) and close to a trillion parameters are dominating the realm of most capable language models. However, the massive model scale poses significant challenges for the underlying…

We propose MindVL, a multimodal large language model (MLLMs) trained on Ascend NPUs. The training of state-of-the-art MLLMs is often confined to a limited set of hardware platforms and relies heavily on massive, undisclosed data recipes,…

Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs, often riddled with numerous challenges…

Efficient LLM serving must balance throughput and latency across diverse, bursty workloads. We introduce StreamServe, a disaggregated prefill decode serving architecture that combines metric aware routing across compute lanes with adaptive…

Large language models (LLMs) such as GPTs and Mixtral-8x7B have revolutionized machine intelligence due to their exceptional abilities in generic ML tasks. Transiting LLMs from datacenters to edge devices brings benefits like better privacy…

Serving Large Language Models (LLMs) can benefit immensely from parallelizing both the model and input requests across multiple devices, but incoming workloads exhibit substantial spatial and temporal heterogeneity. Spatially, workloads…

Most end-to-end (E2E) speech recognition models are composed of encoder and decoder blocks that perform acoustic and language modeling functions. Pretrained large language models (LLMs) have the potential to improve the performance of E2E…

Large multimodal models (LMMs) demonstrate impressive capabilities in understanding images, videos, and audio beyond text. However, efficiently serving LMMs in production environments poses significant challenges due to their complex…

Large Language Models (LLMs) with Mixture-of-Expert (MoE) architectures achieve superior model performance with reduced computation costs, but at the cost of high memory capacity and bandwidth requirements. Near-Memory Processing (NMP)…

Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing…

Serverless computing has emerged as a compelling solution for cloud-based model inference. However, as modern large language models (LLMs) continue to grow in size, existing serverless platforms often face substantial model startup…

LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit…

Large language model (LLM) serving is becoming an increasingly critical workload for cloud providers. Existing LLM serving systems focus on interactive requests, such as chatbots and coding assistants, with tight latency SLO requirements.…

Large language model (LLM) inference serving systems are essential to various LLM-based applications. As demand for LLM services continues to grow, scaling these systems to handle high request rates while meeting latency Service-Level…

Large language model (LLM) serving demands low latency and high throughput, but high load variability makes it challenging to achieve high GPU utilization. In this paper, we identify a synergetic but overlooked opportunity to co-serve…

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…

Large Language Model (LLM) serving must meet stringent Service Level Objectives (SLOs) for both the prefill and decode phases. Some existing solutions disaggregate the two phases, causing potential resource idleness or compute redundancy.…

Meeting growing demands for low latency and cost efficiency in production-grade large language model (LLM) serving systems requires integrating advanced optimization techniques. However, dynamic and unpredictable input-output lengths of…