相关论文: Birbal: An efficient 7B instruct-model fine-tuned …

Sample efficiency has been a key issue in reinforcement learning (RL). An efficient agent must be able to leverage its prior experiences to quickly adapt to similar, but new tasks and situations. Meta-RL is one attempt at formalizing and…

Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training…

The immense computational cost of training Large Language Models (LLMs) presents a major barrier to innovation. While FP8 training offers a promising solution with significant theoretical efficiency gains, its widespread adoption has been…

Due to time constraints, mental health professionals in China are unable to offer patients prolonged talk therapy, leaving a gap in care for patients with psychological disorders, including aberrant sleep and eating patterns, maladaptive…

The rapid development of large language models (LLM) has greatly enhanced everyday applications. While many FPGA-based accelerators, with flexibility for fine-grained data control, exhibit superior speed and energy efficiency compared to…

We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pretrained…

We present MegaBeam-Mistral-7B, a language model that supports 512K-token context length. Our work addresses practical limitations in long-context training, supporting real-world tasks such as compliance monitoring and verification.…

Recently developed large language models (LLMs) such as ChatGPT, Claude, and Llama have demonstrated impressive abilities, and even surpass human-level performance in several tasks. Despite their success, the resource-intensive demands of…

Interactive notebook programming is universal in modern ML and AI workflows, with interactive deep learning training (IDLT) emerging as a dominant use case. To ensure responsiveness, platforms like Jupyter and Colab reserve GPUs for…

Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging…

In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations prevalent in such systems. To address these issues, we present two…

Modern large language foundation models (LLM) have now entered the daily lives of millions of users. We ask a natural question whether it is possible to customize LLM for every user or every task. From system and industrial economy…

Parameter Efficient Finetuning (PEFT) has emerged as a viable solution for improving the performance of Large Language Models (LLMs) without requiring massive resources and compute. Prior work on multilingual evaluation has shown that there…

The rapid advancement of Large Language Models (LLMs) has improved text understanding and generation but poses challenges in computational resources. This study proposes a curriculum learning-inspired, data-centric training strategy that…

In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential execution of computation and communication. This results in…

Performance optimization can be a daunting task especially as the hardware architecture becomes more and more complex. This paper takes a kernel from the Materials Science code BerkeleyGW, and demonstrates a few performance analysis and…

The rapid growth of scientific machine learning (SciML) has accelerated discovery across diverse domains, yet designing effective SciML models remains a challenging task. In practice, building such models often requires substantial prior…

Large language model (LLM) inference performance is increasingly bottlenecked by the memory wall. While GPUs continue to scale raw compute throughput, they struggle to deliver scalable performance for memory bandwidth bound workloads. This…

Pretraining auto-regressive large language models~(LLMs) with retrieval demonstrates better perplexity and factual accuracy by leveraging external databases. However, the size of existing pretrained retrieval-augmented LLM is still limited…

While Large Language Models (LLMs) show significant potential in hardware engineering, current benchmarks suffer from saturation and limited task diversity, failing to reflect LLMs' performance in real industrial workflows. To address this…