Related papers: LoongServe: Efficiently Serving Long-Context Large…
Serving large language models (LLMs) to millions of users requires efficient resource allocation and parallelism strategies. It is a labor intensive trial-and-error process to find such a strategy. We present BestServe, a novel framework…
Recent advances in Large Language Models (LLMs) have yielded impressive successes on many language tasks. However, efficient processing of long contexts using LLMs remains a significant challenge. We introduce \textbf{EpMAN} -- a method for…
Large Language Models (LLMs) have demonstrated remarkable capabilities in comprehending and analyzing lengthy sequential inputs, owing to their extensive context windows that allow processing millions of tokens in a single forward pass.…
Large language models (LLMs) have proven to be effective tools for a wide range of natural language processing (NLP) applications. Although many LLMs are multilingual, most remain English-centric and perform poorly on low-resource…
LLM serving is increasingly multi-tenant: the same deployment must handle latency-critical interactive requests and more relaxed background workloads under a fixed GPU budget. This creates a tiered-SLO setting where maximizing overall…
The increasing demand for intelligent mobile applications has made multi-agent collaboration with Transformer-based large language models (LLMs) essential in mobile edge computing (MEC) networks. However, training LLMs in such environments…
While many advanced LLMs are designed to handle long sequence data, we can still observe notable quality degradation even within the sequence limit. In this work, we introduce a novel approach called Scaling to Emphasize Attention for…
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level…
High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…
The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where…
Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible…
Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming…
We survey the large language model (LLM) serving area to understand the intricate dynamics between cost-efficiency and accuracy, which is magnified by the growing need for longer contextual understanding when deploying models at a massive…
Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail…
Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on…
Recent breakthroughs in large Language Models (LLMs) have enabled various generative tasks on a single model. Real-world services (e.g., OpenAI's ChatGPT [27]) powered by an LLM often concurrently support latency-critical requests for…
While long-context large language models (LLMs) exhibit remarkable document processing capabilities, their prohibitively high training costs often hinder customized applications. To mitigate this issue, we propose \textit{Sequential…
In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to…
Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we propose Extensible…
Deploying Large Language Model (LLM) services at the edge benefits latency-sensitive and privacy-aware applications. However, the stateless nature of LLMs makes managing user context (e.g., sessions, preferences) across geo-distributed edge…