Related papers: PipeInfer: Accelerating LLM Inference using Asynch…
Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thorough exploration. However, increased compute often comes at…
RAPID-LLM is a unified performance modeling framework for large language model (LLM) training and inference on GPU clusters. It couples a DeepFlow-based frontend that generates hardware-aware, operator-level Chakra execution traces from an…
Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning methods address this by surpassing the capabilities of…
Large language models (LLMs) hold tremendous potential for addressing numerous real-world challenges, yet they typically demand significant computational resources and memory. Deploying LLMs onto a resource-limited hardware device with…
We propose LLMA, an LLM accelerator to losslessly speed up Large Language Model (LLM) inference with references. LLMA is motivated by the observation that there are abundant identical text spans between the decoding result by an LLM and the…
Speculative decoding has emerged as a promising technique for large language model (LLM) inference by accelerating autoregressive decoding via draft-then-verify. This paper studies a new edge scenario with multi-user inference, where draft…
Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases. However, retrievals from large databases can constitute a substantial portion of the overall…
The emergence of large language models (LLMs) relies heavily on distributed training strategies, among which pipeline parallelism plays a crucial role. As LLMs' training sequence length extends to 32k or even 128k, the current pipeline…
The rapid growth of large-language models (LLMs) is driving a new wave of specialized hardware for inference. This paper presents the first workload-centric, cross-architectural performance study of commercial AI accelerators, spanning…
Last few years have seen unprecedented advances in capabilities of Large Language Models (LLMs). These advancements promise to benefit a vast array of application domains. However, due to their immense size, performing inference with LLMs…
Assessing ways in which Language Models can reduce their hallucinations and improve the outputs' quality is crucial to ensure their large-scale use. However, methods such as fine-tuning on domain-specific data or the training of a separate…
Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference time, raising the natural question: when is the extra cost of…
To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…
Spiking Neural Network (SNN) inference has a clear potential for high energy efficiency as computation is triggered by events. However, the inherent sparsity of events poses challenges for conventional computing systems, driving the…
While scaling laws have been continuously validated in large language models (LLMs) with increasing model parameters, the inherent tension between the inference demands of LLMs and the limited resources of edge devices poses a critical…
Tree-search-based reasoning methods have significantly enhanced the reasoning capability of large language models (LLMs) by facilitating the exploration of multiple intermediate reasoning steps, i.e., thoughts. However, these methods suffer…
The immense model sizes of large language models (LLMs) challenge deployment on memory-limited consumer GPUs. Although model compression and parameter offloading are common strategies to address memory limitations, compression can degrade…
Large language models (LLMs) exhibit remarkable reasoning capabilities across diverse downstream tasks. However, their autoregressive nature leads to substantial inference latency, posing challenges for real-time applications. Speculative…
As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes crucial, especially for…
Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…