Showing 1–10 of 10 results for author: Gonugondla, S

AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following

Authors: Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G. Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Awadalla, Manaal Faruqui

Abstract: Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF)-especially for complex, multi-turn, and system-prompted instructions-remains a significant challenge. Rigorous evaluation and effective training for such capabilities are hindered by the lack of high-quality, human-annotated benchmarks and reliable, interpr… ▽ More Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF)-especially for complex, multi-turn, and system-prompted instructions-remains a significant challenge. Rigorous evaluation and effective training for such capabilities are hindered by the lack of high-quality, human-annotated benchmarks and reliable, interpretable reward signals. In this work, we introduce AdvancedIF (we will release this benchmark soon), a comprehensive benchmark featuring over 1,600 prompts and expert-curated rubrics that assess LLMs ability to follow complex, multi-turn, and system-level instructions. We further propose RIFL (Rubric-based Instruction-Following Learning), a novel post-training pipeline that leverages rubric generation, a finetuned rubric verifier, and reward shaping to enable effective reinforcement learning for instruction following. Extensive experiments demonstrate that RIFL substantially improves the instruction-following abilities of LLMs, achieving a 6.7% absolute gain on AdvancedIF and strong results on public benchmarks. Our ablation studies confirm the effectiveness of each component in RIFL. This work establishes rubrics as a powerful tool for both training and evaluating advanced IF in LLMs, paving the way for more capable and reliable AI systems. △ Less

Submitted 26 November, 2025; v1 submitted 13 November, 2025; originally announced November 2025.

The N-Grammys: Accelerating Autoregressive Inference with Learning-Free Batched Speculation

Authors: Lawrence Stewart, Matthew Trager, Sujan Kumar Gonugondla, Stefano Soatto

Abstract: Speculative decoding aims to speed up autoregressive generation of a language model by verifying in parallel the tokens generated by a smaller draft model.In this work, we explore the effectiveness of learning-free, negligible-cost draft strategies, namely $N$-grams obtained from the model weights and the context. While the predicted next token of the base model is rarely the top prediction of the… ▽ More Speculative decoding aims to speed up autoregressive generation of a language model by verifying in parallel the tokens generated by a smaller draft model.In this work, we explore the effectiveness of learning-free, negligible-cost draft strategies, namely $N$-grams obtained from the model weights and the context. While the predicted next token of the base model is rarely the top prediction of these simple strategies, we observe that it is often within their top-$k$ predictions for small $k$. Based on this, we show that combinations of simple strategies can achieve significant inference speedups over different tasks. The overall performance is comparable to more complex methods, yet does not require expensive preprocessing or modification of the base model, and allows for seamless `plug-and-play' integration into pipelines. △ Less

Submitted 6 November, 2024; originally announced November 2024.

Journal ref: ENLSP-IV 2024 - 4th NeurIPS Efficient Natural Language and Speech Processing Workshop, Dec 2024, Vancouver, Canada

Approximately Aligned Decoding

Authors: Daniel Melcer, Sujan Gonugondla, Pramuditha Perera, Haifeng Qian, Wen-Hao Chiang, Yanjun Wang, Nihal Jain, Pranav Garg, Xiaofei Ma, Anoop Deoras

Abstract: It is common to reject undesired outputs of Large Language Models (LLMs); however, current methods to do so require an excessive amount of computation to re-sample after a rejection, or distort the distribution of outputs by constraining the output to highly improbable tokens. We present a method, Approximately Aligned Decoding (AprAD), to balance the distortion of the output distribution with com… ▽ More It is common to reject undesired outputs of Large Language Models (LLMs); however, current methods to do so require an excessive amount of computation to re-sample after a rejection, or distort the distribution of outputs by constraining the output to highly improbable tokens. We present a method, Approximately Aligned Decoding (AprAD), to balance the distortion of the output distribution with computational efficiency, inspired by algorithms from the speculative decoding literature. AprAD allows for the generation of long sequences of text with difficult-to-satisfy constraints, while amplifying low probability outputs much less compared to existing methods. We show through a series of experiments that the task-specific performance of AprAD is comparable to methods that do not distort the output distribution, while being much more computationally efficient. △ Less

Submitted 7 October, 2025; v1 submitted 1 October, 2024; originally announced October 2024.

Comments: NeurIPS 2025 version; 10 pages, 35 total

BASS: Batched Attention-optimized Speculative Sampling

Authors: Haifeng Qian, Sujan Kumar Gonugondla, Sungsoo Ha, Mingyue Shang, Sanjay Krishna Gouda, Ramesh Nallapati, Sudipta Sengupta, Xiaofei Ma, Anoop Deoras

Abstract: Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generative AI applications often require multiple responses and how to perform speculative decoding in a batched setting while preserving its latency benefits poses non-trivial challenges.… ▽ More Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generative AI applications often require multiple responses and how to perform speculative decoding in a batched setting while preserving its latency benefits poses non-trivial challenges. This paper describes a system of batched speculative decoding that sets a new state of the art in multi-sequence generation latency and that demonstrates superior GPU utilization as well as quality of generations within a time budget. For example, for a 7.8B-size model on a single A100 GPU and with a batch size of 8, each sequence is generated at an average speed of 5.8ms per token, the overall throughput being 1.1K tokens per second. These results represent state-of-the-art latency and a 2.15X speed-up over optimized regular decoding. Within a time budget that regular decoding does not finish, our system is able to generate sequences with HumanEval Pass@First of 43% and Pass@All of 61%, far exceeding what's feasible with single-sequence speculative decoding. Our peak GPU utilization during decoding reaches as high as 15.8%, more than 3X the highest of that of regular decoding and around 10X of single-sequence speculative decoding. △ Less

Submitted 26 June, 2024; v1 submitted 24 April, 2024; originally announced April 2024.

Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs

Authors: Ben Athiwaratkun, Sujan Kumar Gonugondla, Sanjay Krishna Gouda, Haifeng Qian, Hantian Ding, Qing Sun, Jun Wang, Jiacheng Guo, Liangfu Chen, Parminder Bhatia, Ramesh Nallapati, Sudipta Sengupta, Bing Xiang

Abstract: This study introduces bifurcated attention, a method designed to enhance language model inference in shared-context batch decoding scenarios. Our approach addresses the challenge of redundant memory IO costs, a critical factor contributing to latency in high batch sizes and extended context lengths. Bifurcated attention achieves this by strategically dividing the attention mechanism during increme… ▽ More This study introduces bifurcated attention, a method designed to enhance language model inference in shared-context batch decoding scenarios. Our approach addresses the challenge of redundant memory IO costs, a critical factor contributing to latency in high batch sizes and extended context lengths. Bifurcated attention achieves this by strategically dividing the attention mechanism during incremental decoding into two separate GEMM operations: one focusing on the KV cache from prefill, and another on the decoding process itself. While maintaining the computational load (FLOPs) of standard attention mechanisms, bifurcated attention ensures precise computation with significantly reduced memory IO. Our empirical results show over 2.1$\times$ speedup when sampling 16 output sequences and more than 6.2$\times$ speedup when sampling 32 sequences at context lengths exceeding 8k tokens on a 7B model that uses multi-head attention. The efficiency gains from bifurcated attention translate into lower latency, making it particularly suitable for real-time applications. For instance, it enables massively parallel answer generation without substantially increasing latency, thus enhancing performance when integrated with post-processing techniques such as re-ranking. △ Less

Submitted 11 July, 2024; v1 submitted 13 March, 2024; originally announced March 2024.

Token Alignment via Character Matching for Subword Completion

Authors: Ben Athiwaratkun, Shiqi Wang, Mingyue Shang, Yuchen Tian, Zijian Wang, Sujan Kumar Gonugondla, Sanjay Krishna Gouda, Rob Kwiatowski, Ramesh Nallapati, Bing Xiang

Abstract: Generative models, widely utilized in various applications, can often struggle with prompts corresponding to partial tokens. This struggle stems from tokenization, where partial tokens fall out of distribution during inference, leading to incorrect or nonsensical outputs. This paper examines a technique to alleviate the tokenization artifact on text completion in generative models, maintaining per… ▽ More Generative models, widely utilized in various applications, can often struggle with prompts corresponding to partial tokens. This struggle stems from tokenization, where partial tokens fall out of distribution during inference, leading to incorrect or nonsensical outputs. This paper examines a technique to alleviate the tokenization artifact on text completion in generative models, maintaining performance even in regular non-subword cases. The method, termed token alignment, involves backtracking to the last complete tokens and ensuring the model's generation aligns with the prompt. This approach showcases marked improvement across many partial token scenarios, including nuanced cases like space-prefix and partial indentation, with only a minor time increase. The technique and analysis detailed in this paper contribute to the continuous advancement of generative models in handling partial inputs, bearing relevance for applications like code completion and text autocompletion. △ Less

Submitted 13 March, 2024; originally announced March 2024.

Greener yet Powerful: Taming Large Code Generation Models with Quantization

Authors: Xiaokai Wei, Sujan Gonugondla, Wasi Ahmad, Shiqi Wang, Baishakhi Ray, Haifeng Qian, Xiaopeng Li, Varun Kumar, Zijian Wang, Yuchen Tian, Qing Sun, Ben Athiwaratkun, Mingyue Shang, Murali Krishna Ramanathan, Parminder Bhatia, Bing Xiang

Abstract: ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have substantially pushed the boundary of code generation and achieved impressive performance. Despite their great power, the huge number of model parameters poses a significant thr… ▽ More ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have substantially pushed the boundary of code generation and achieved impressive performance. Despite their great power, the huge number of model parameters poses a significant threat to adapting them in a regular software development environment, where a developer might use a standard laptop or mid-size server to develop her code. Such large models incur significant resource usage (in terms of memory, latency, and dollars) as well as carbon footprint. Model compression is a promising approach to address these challenges. Several techniques are proposed to compress large pretrained models typically used for vision or textual data. Out of many available compression techniques, we identified that quantization is mostly applicable for code generation task as it does not require significant retraining cost. As quantization represents model parameters with lower-bit integer (e.g., int8), the model size and runtime latency would both benefit from such int representation. We extensively study the impact of quantized model on code generation tasks across different dimension: (i) resource usage and carbon footprint, (ii) accuracy, and (iii) robustness. To this end, through systematic experiments we find a recipe of quantization technique that could run even a $6$B model in a regular laptop without significant accuracy or robustness degradation. We further found the recipe is readily applicable to code summarization task as well. △ Less

Submitted 9 March, 2023; originally announced March 2023.

Comments: 10 pages, 7 figures, 10 tables

Multi-lingual Evaluation of Code Generation Models

Authors: Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang, Xiaopeng Li, Yuchen Tian, Ming Tan, Wasi Uddin Ahmad, Shiqi Wang, Qing Sun, Mingyue Shang, Sujan Kumar Gonugondla, Hantian Ding, Varun Kumar, Nathan Fulton, Arash Farahani, Siddhartha Jain, Robert Giaquinto, Haifeng Qian, Murali Krishna Ramanathan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Sudipta Sengupta, Dan Roth, Bing Xiang

Abstract: We present new benchmarks on evaluation code generation models: MBXP and Multilingual HumanEval, and MathQA-X. These datasets cover over 10 programming languages and are generated using a scalable conversion framework that transpiles prompts and test cases from the original Python datasets into the corresponding data in the target language. Using these benchmarks, we are able to assess the perform… ▽ More We present new benchmarks on evaluation code generation models: MBXP and Multilingual HumanEval, and MathQA-X. These datasets cover over 10 programming languages and are generated using a scalable conversion framework that transpiles prompts and test cases from the original Python datasets into the corresponding data in the target language. Using these benchmarks, we are able to assess the performance of code generation models in a multi-lingual fashion, and discovered generalization ability of language models on out-of-domain languages, advantages of multi-lingual models over mono-lingual, the ability of few-shot prompting to teach the model new languages, and zero-shot translation abilities even on mono-lingual settings. Furthermore, we use our code generation model to perform large-scale bootstrapping to obtain synthetic canonical solutions in several languages, which can be used for other code-related evaluations such as code insertion, robustness, or summarization tasks. Overall, our benchmarks represents a significant step towards a deeper understanding of language models' code generation abilities. We publicly release our code and datasets at https://github.com/amazon-research/mxeval. △ Less

Submitted 28 March, 2023; v1 submitted 26 October, 2022; originally announced October 2022.

Comments: Code and data release: https://github.com/amazon-research/mxeval

Fundamental Limits on Energy-Delay-Accuracy of In-memory Architectures in Inference Applications

Authors: Sujan Kumar Gonugondla, Charbel Sakr, Hassan Dbouk, Naresh R. Shanbhag

Abstract: This paper obtains fundamental limits on the computational precision of in-memory computing architectures (IMCs). An IMC noise model and associated SNR metrics are defined and their interrelationships analyzed to show that the accuracy of IMCs is fundamentally limited by the compute SNR ($\text{SNR}_{\text{a}}$) of its analog core, and that activation, weight and output precision needs to be assig… ▽ More This paper obtains fundamental limits on the computational precision of in-memory computing architectures (IMCs). An IMC noise model and associated SNR metrics are defined and their interrelationships analyzed to show that the accuracy of IMCs is fundamentally limited by the compute SNR ($\text{SNR}_{\text{a}}$) of its analog core, and that activation, weight and output precision needs to be assigned appropriately for the final output SNR $\text{SNR}_{\text{T}} \rightarrow \text{SNR}_{\text{a}}$. The minimum precision criterion (MPC) is proposed to minimize the ADC precision. Three in-memory compute models - charge summing (QS), current summing (IS) and charge redistribution (QR) - are shown to underlie most known IMCs. Noise, energy and delay expressions for the compute models are developed and employed to derive expressions for the SNR, ADC precision, energy, and latency of IMCs. The compute SNR expressions are validated via Monte Carlo simulations in a 65 nm CMOS process. For a 512 row SRAM array, it is shown that: 1) IMCs have an upper bound on their maximum achievable $\text{SNR}_{\text{a}}$ due to constraints on energy, area and voltage swing, and this upper bound reduces with technology scaling for QS-based architectures; 2) MPC enables $\text{SNR}_{\text{T}} \rightarrow \text{SNR}_{\text{a}}$ to be realized with minimal ADC precision; 3) QS-based (QR-based) architectures are preferred for low (high) compute SNR scenarios. △ Less

Submitted 25 December, 2020; originally announced December 2020.

Comments: 14 pages, 13 figures

A 481pJ/decision 3.4M decision/s Multifunctional Deep In-memory Inference Processor using Standard 6T SRAM Array

Authors: Mingu Kang, Sujan Gonugondla, Ameya Patil, Naresh Shanbhag

Abstract: This paper describes a multi-functional deep in-memory processor for inference applications. Deep in-memory processing is achieved by embedding pitch-matched low-SNR analog processing into a standard 6T 16KB SRAM array in 65 nm CMOS. Four applications are demonstrated. The prototype achieves up to 5.6X (9.7X estimated for multi-bank scenario) energy savings with negligible (<1%) accuracy degradati… ▽ More This paper describes a multi-functional deep in-memory processor for inference applications. Deep in-memory processing is achieved by embedding pitch-matched low-SNR analog processing into a standard 6T 16KB SRAM array in 65 nm CMOS. Four applications are demonstrated. The prototype achieves up to 5.6X (9.7X estimated for multi-bank scenario) energy savings with negligible (<1%) accuracy degradation in all four applications as compared to the conventional architecture. △ Less

Submitted 24 October, 2016; originally announced October 2016.