Related papers: Tangram: Accelerating Serverless LLM Loading throu…
Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…
Serverless computing is transforming cloud application development, but the performance-cost trade-offs of control plane designs remain poorly understood due to a lack of open, cross-platform benchmarks and detailed system analyses. In this…
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…
This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text…
The increasing complexity of large language models (LLMs) necessitates efficient training strategies to mitigate the high computational costs associated with distributed training. A significant bottleneck in this process is gradient…
The AI datacenters are currently being deployed on a large scale to support the training and deployment of power-intensive large-language models (LLMs). Extensive amount of computation and cooling required in datacenters increase concerns…
Transformers and large language models~(LLMs) have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of parameters and keep increasing. Under these circumstances, the training of transformers is very…
The rapid digitization and the increasing use of emerging technologies such as AI models have significantly contributed to the emissions of computing infrastructure. Efforts to mitigate this impact typically focus on the infrastructure…
Training Large Language Models (LLMs) is plagued by long training times and massive energy consumption, with modern models requiring months of computation and gigawatt-hours of electricity. In light of these challenges,we introduce…
With the widespread adoption of Large Language Models (LLMs), the demand for high-performance LLM inference services continues to grow. To meet this demand, a growing number of AI accelerators have been proposed, such as Google TPU, Huawei…
Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demands low latency for LLM inference. Existing LLM serving systems use…
Most Large Language Models (LLMs) are currently deployed in the cloud, with users relying on internet connectivity for access. However, this paradigm faces challenges such as network latency, privacy concerns, and bandwidth limits. Thus,…
Large language models (LLMs) have demonstrated exceptional performance across a variety of tasks. However, their substantial scale leads to significant computational resource consumption during inference, resulting in high costs.…
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…
Large reasoning models (LRMs) achieve strong accuracy through test-time scaling, generating longer chains of thought or sampling multiple solutions, but at steep costs in tokens and latency. We argue that memory is a core ingredient for…
The rapid increase in the number of parameters in large language models (LLMs) has significantly increased the cost involved in fine-tuning and retraining LLMs, a necessity for keeping models up to date and improving accuracy.…
Large language models (LLMs) rely on Key-Value (KV) cache to reduce time-to-first-token (TTFT) latency, but existing disk-based KV cache systems using file-per-object layouts suffer from severe scalability bottlenecks due to file system…
Retrieval-Augmented Generation (RAG) enhances large language model (LLM) generation quality by incorporating relevant external knowledge. However, deploying RAG on consumer-grade platforms is challenging due to limited memory and the…
Serverless computing paradigm has become more ingrained into the industry, as it offers a cheap alternative for application development and deployment. This new paradigm has also created new kinds of problems for the developer, who needs to…
Deploying large language model (LLM) inference at scale requires jointly selecting base models, provisioning heterogeneous GPUs, configuring parallelism, and distributing workloads under tight latency, accuracy, and budget constraints.…