Tianle Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tianle Cai has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Yikang Shen
MIT-IBM Watson AI Lab
3 shared publications - Chuang Gan
UMass Amherst, Amherst, MA, USA
2 shared publications - Delin Chen
UMass Amherst
2 shared publications - Di He
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China
2 shared publications - Di He
Microsoft Research Beijing China
2 shared publications - Jason D. Lee
Princeton University
2 shared publications
Latest Publications
- 26 October 2024
- Published by Springer Nature
- p. 286-302
FlexAttention for Efficient High-Resolution Vision-Language Models
- 26 October 2024
- Published by Springer Nature
- p. 286-302
FlexAttention for Efficient High-Resolution Vision-Language Models
- Open Access
FlexAttention for Efficient High-Resolution Vision-Language Models
Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we propose FlexAttention, a flexible attention mechanism for efficient high-resolution vision-language models. Specifically, a high-resolution image is encoded both as high-resolution tokens and low-resolution tokens, where only the low-resolution tokens and a few selected high-resolution tokens are utilized to calculate the attention map, which greatly shrinks the computational cost. The high-resolution tokens are selected via a high-resolution selection module which could retrieve tokens of relevant regions based on an input attention map. The selected high-resolution tokens are then concatenated to the low-resolution tokens and text tokens, and input to a hierarchical self-attention layer which produces an attention map that could be used for the next-step high-resolution token selection. The hierarchical self-attention process and high-resolution token selection process are performed iteratively for each attention layer. Experiments on multimodal benchmarks prove that our FlexAttention outperforms existing high-resolution VLMs (e.g., relatively ~9% in V* Bench, ~7% in TextVQA), while also significantly reducing the computational cost by nearly 40%.
Open AccessFlexAttention for Efficient High-Resolution Vision-Language Models
Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we propose FlexAttention, a flexible attention mechanism for efficient high-resolution vision-language models. Specifically, a high-resolution image is encoded both as high-resolution tokens and low-resolution tokens, where only the low-resolution tokens and a few selected high-resolution tokens are utilized to calculate the attention map, which greatly shrinks the computational cost. The high-resolution tokens are selected via a high-resolution selection module which could retrieve tokens of relevant regions based on an input attention map. The selected high-resolution tokens are then concatenated to the low-resolution tokens and text tokens, and input to a hierarchical self-attention layer which produces an attention map that could be used for the next-step high-resolution token selection. The hierarchical self-attention process and high-resolution token selection process are performed iteratively for each attention layer. Experiments on multimodal benchmarks prove that our FlexAttention outperforms existing high-resolution VLMs (e.g., relatively ~9% in V* Bench, ~7% in TextVQA), while also significantly reducing the computational cost by nearly 40%.
- Open Access
JetMoE: Reaching Llama2 Performance with 0.1M Dollars
Large Language Models (LLMs) have achieved remarkable results, but their increasing resource demand has become a major obstacle to the development of powerful and accessible super-human intelligence. This report introduces JetMoE-8B, a new LLM trained with less than $0.1 million, using 1.25T tokens from carefully mixed open-source corpora and 30,000 H100 GPU hours. Despite its low cost, the JetMoE-8B demonstrates impressive performance, with JetMoE-8B outperforming the Llama2-7B model and JetMoE-8B-Chat surpassing the Llama2-13B-Chat model. These results suggest that LLM training can be much more cost-effective than generally thought. JetMoE-8B is based on an efficient Sparsely-gated Mixture-of-Experts (SMoE) architecture, composed of attention and feedforward experts. Both layers are sparsely activated, allowing JetMoE-8B to have 8B parameters while only activating 2B for each input token, reducing inference computation by about 70% compared to Llama2-7B. Moreover, JetMoE-8B is highly open and academia-friendly, using only public datasets and training code. All training parameters and data mixtures have been detailed in this report to facilitate future efforts in the development of open foundation models. This transparency aims to encourage collaboration and further advancements in the field of accessible and efficient LLMs. The model weights are publicly available at https://github.com/myshell-ai/JetMoE.
Open AccessJetMoE: Reaching Llama2 Performance with 0.1M Dollars
Large Language Models (LLMs) have achieved remarkable results, but their increasing resource demand has become a major obstacle to the development of powerful and accessible super-human intelligence. This report introduces JetMoE-8B, a new LLM trained with less than $0.1 million, using 1.25T tokens from carefully mixed open-source corpora and 30,000 H100 GPU hours. Despite its low cost, the JetMoE-8B demonstrates impressive performance, with JetMoE-8B outperforming the Llama2-7B model and JetMoE-8B-Chat surpassing the Llama2-13B-Chat model. These results suggest that LLM training can be much more cost-effective than generally thought. JetMoE-8B is based on an efficient Sparsely-gated Mixture-of-Experts (SMoE) architecture, composed of attention and feedforward experts. Both layers are sparsely activated, allowing JetMoE-8B to have 8B parameters while only activating 2B for each input token, reducing inference computation by about 70% compared to Llama2-7B. Moreover, JetMoE-8B is highly open and academia-friendly, using only public datasets and training code. All training parameters and data mixtures have been detailed in this report to facilitate future efforts in the development of open foundation models. This transparency aims to encourage collaboration and further advancements in the field of accessible and efficient LLMs. The model weights are publicly available at https://github.com/myshell-ai/JetMoE.
- Open Access
REST: Retrieval-Based Speculative Decoding
We introduce Retrieval-Based Speculative Decoding (REST), a novel algorithm designed to speed up language model generation. The key insight driving the development of REST is the observation that the process of text generation often includes certain common phases and patterns. Unlike previous methods that rely on a draft language model for speculative decoding, REST harnesses the power of retrieval to generate draft tokens. This method draws from the reservoir of existing knowledge, retrieving and employing relevant tokens based on the current context. Its plug-and-play nature allows for seamless integration and acceleration of any language models, all without necessitating additional training. When benchmarked on 7B and 13B language models in a single-batch setting, REST achieves a significant speedup of 1.62X to 2.36X on code or text generation. The code of REST is available at https://github.com/FasterDecoding/REST.
Open AccessREST: Retrieval-Based Speculative Decoding
We introduce Retrieval-Based Speculative Decoding (REST), a novel algorithm designed to speed up language model generation. The key insight driving the development of REST is the observation that the process of text generation often includes certain common phases and patterns. Unlike previous methods that rely on a draft language model for speculative decoding, REST harnesses the power of retrieval to generate draft tokens. This method draws from the reservoir of existing knowledge, retrieving and employing relevant tokens based on the current context. Its plug-and-play nature allows for seamless integration and acceleration of any language models, all without necessitating additional training. When benchmarked on 7B and 13B language models in a single-batch setting, REST achieves a significant speedup of 1.62X to 2.36X on code or text generation. The code of REST is available at https://github.com/FasterDecoding/REST.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1582-1595
REST: Retrieval-Based Speculative Decoding
Zhenyu He, Zexuan Zhong, Tianle Cai, Jason Lee, Di He. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1582-1595
Open AccessREST: Retrieval-Based Speculative Decoding
Zhenyu He, Zexuan Zhong, Tianle Cai, Jason Lee, Di He. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- Open Access
Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original attention, leading to sub-quadratic or even linear-complexity Transformer architectures. However, we show that these methods cannot be applied to more powerful attention modules that go beyond the dot-then-exponentiate style, e.g., Transformers with relative positional encoding (RPE). Since in many state-of-the-art models, relative positional encoding is used as default, designing efficient Transformers that can incorporate RPE is appealing. In this paper, we propose a novel way to accelerate attention calculation for Transformers with RPE on top of the kernelized attention. Based upon the observation that relative positional encoding forms a Toeplitz matrix, we mathematically show that kernelized attention with RPE can be calculated efficiently using Fast Fourier Transform (FFT). With FFT, our method achieves $\mathcal{O}(n\log n)$ time complexity. Interestingly, we further demonstrate that properly using relative positional encoding can mitigate the training instability problem of vanilla kernelized attention. On a wide range of tasks, we empirically show that our models can be trained from scratch without any optimization issues. The learned model performs better than many efficient Transformer variants and is faster than standard Transformer in the long-sequence regime.Open AccessStable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original attention, leading to sub-quadratic or even linear-complexity Transformer architectures. However, we show that these methods cannot be applied to more powerful attention modules that go beyond the dot-then-exponentiate style, e.g., Transformers with relative positional encoding (RPE). Since in many state-of-the-art models, relative positional encoding is used as default, designing efficient Transformers that can incorporate RPE is appealing. In this paper, we propose a novel way to accelerate attention calculation for Transformers with RPE on top of the kernelized attention. Based upon the observation that relative positional encoding forms a Toeplitz matrix, we mathematically show that kernelized attention with RPE can be calculated efficiently using Fast Fourier Transform (FFT). With FFT, our method achieves $\mathcal{O}(n\log n)$ time complexity. Interestingly, we further demonstrate that properly using relative positional encoding can mitigate the training instability problem of vanilla kernelized attention. On a wide range of tasks, we empirically show that our models can be trained from scratch without any optimization issues. The learned model performs better than many efficient Transformer variants and is faster than standard Transformer in the long-sequence regime. - Open Access
First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track
In this technical report, we present our solution of KDD Cup 2021 OGB Large-Scale Challenge - PCQM4M-LSC Track. We adopt Graphormer and ExpC as our basic models. We train each model by 8-fold cross-validation, and additionally train two Graphormer models on the union of training and validation sets with different random seeds. For final submission, we use a naive ensemble for these 18 models by taking average of their outputs. Using our method, our team MachineLearning achieved 0.1200 MAE on test set, which won the first place in KDD Cup graph prediction track.
Open AccessFirst Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track
In this technical report, we present our solution of KDD Cup 2021 OGB Large-Scale Challenge - PCQM4M-LSC Track. We adopt Graphormer and ExpC as our basic models. We train each model by 8-fold cross-validation, and additionally train two Graphormer models on the union of training and validation sets with different random seeds. For final submission, we use a naive ensemble for these 18 models by taking average of their outputs. Using our method, our team MachineLearning achieved 0.1200 MAE on test set, which won the first place in KDD Cup graph prediction track.