arXiv subjects

Yash Akhauri

Publications and source records attributed to Yash Akhauri.

At least 19 recordsLinked to original sources

arXiv2026

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential token generation. To overcome this bottleneck, we introduce diffusion-augmented LLMs, a new class of models that defines an AR model distribution while using diffusion to draw multiple tokens in parallel from that distribution. We decouple the parameters of these models into two sets: AR weights, trained using the standard NTP objective, and lightweight diffusion weights, trained to generate multiple tokens simultaneously. The diffusion weights are learned through a simple Diffusion Distillation phase that adds negligible overhead to existing LLM training pipelines. We also introduce $\Psi$-Spec, a family of samplers that enables lossless acceleration and inference-time scaling at a fixed context length. Unlike speculative decoding, our method requires no separate draft model. Unlike diffusion LLMs (d-LLMs), it accelerates generation without sacrificing the quality of the underlying AR model. The resulting models, called Uno, can be trained from scratch or built by augmenting existing open-weight AR LLMs. Uno achieves higher throughput than leading speculative-decoding methods at every evaluated batch size and delivers up to $3\times$ speedups over the base AR model, including at the largest batch size supported by the device. Notably, our 8B Uno model outperforms the leading open d-LLM, the 26B DiffusionGemma, and the proprietary Mercury 2 across all evaluated benchmarks in agentic tool use, coding, and long-context reasoning. We release code and checkpoints at: https://s-sahoo.github.io/uno/

cs.LG↗

arXiv2026

Compute Where it Counts: Self Optimizing Language Models

Efficient LLM inference research has largely focused on reducing the cost of each decoding step (e.g., using quantization, pruning, or sparse attention), typically applying a uniform computation budget to every generated token. In practice, token difficulty varies widely, so static compression can over-compute on easy steps and under-compute on hard ones. We study dynamic budget allocation for autoregressive decoding: learning how much computation to spend per token from within a single model. Self-Optimizing Language Models (SOL) pair a frozen LLM with a lightweight policy network that reads the LLM hidden state and selects a discrete efficiency action at each decode step. Actions can jointly control (i) token-level attention sparsity, (ii) structured activation pruning in the MLP, and (iii) activation quantization bit-width, while leaving the base model weights unchanged. We train the policy with group-relative policy optimization on teacher-forced episodes: the token sequence is fixed, while we sample multiple compute schedules (i.e., "counterfactual" schedules that vary only the efficiency actions for the same token path) and compare their likelihoods under the same supervision. Our reward trades off language-model quality against soft penalties that encourage episode-average budget usage to match a requested target. Across model variants and compute regimes, SOL improves quality at matched budget over static allocation and strong random schedule search, offering a complementary axis for inference-efficiency optimization. SOL discovers a better quality-efficiency pareto-front across all our experiments and improves MMLU accuracy by up to 7.3% over uniform budget allocation strategies.

cs.LG↗

arXiv2025

Regression Language Models for Code

We study code-to-metric regression: predicting numeric outcomes of code executions, a challenging task due to the open-ended nature of programming languages. While prior methods have resorted to heavy and domain-specific feature engineering, we show that a single unified Regression Language Model (RLM) using a frozen LLM encoder can simultaneously predict directly from text, (i) the memory footprint of code across multiple high-level languages such as Python and C++, (ii) the latency of Triton GPU kernels, and (iii) the accuracy and speed of trained neural networks represented in ONNX. In particular, a relatively small 300M parameter RLM based on T5Gemma, obtains >0.9 Spearman-rank on competitive programming submissions from APPS, and a single unified model achieves >0.5 average Spearman-rank across 24 different programming languages from CodeNet. Furthermore, the RLM can obtain the highest average Kendall-Tau of 0.46 on five classic NAS design spaces previously dominated by graph neural networks, and simultaneously predict architecture latencies on numerous hardware platforms.

cs.CL↗

arXiv2025

Performance Prediction for Large Systems via Text-to-Text Regression

In many industries, predicting metric outcomes of large systems is a fundamental problem, driven largely by traditional tabular regression. However, such methods struggle on complex systems data in the wild such as configuration files or system logs, where feature engineering is often infeasible. We propose text-to-text regression as a general, scalable alternative. For predicting resource efficiency on Borg, Google's massive compute cluster scheduling system, a 60M parameter encoder-decoder, trained from random initialization, achieves up to a near perfect 0.99 (0.9 average) rank correlation across the entire fleet, and 100x lower MSE than tabular approaches. The model also easily adapts to new tasks in only 500 few-shot examples and captures the densities of complex outcome distributions. Ablation studies highlight the importance of using encoders, increasing sequence length, and the model's inherent uncertainty quantification. These findings pave the way for universal simulators of real-world outcomes.

cs.LG↗

arXiv2025

Esoteric Language Models: A Family of Any-Order Diffusion LLMs

Diffusion-based language models offer a compelling alternative to autoregressive (AR) models by enabling parallel and controllable generation. Within this family, Masked Diffusion Models (MDMs) currently perform best but still underperform AR models in perplexity and lack key inference-time efficiency features, most notably KV caching. We introduce Eso-LMs, a new family of models that fuses AR and MDM paradigms, smoothly interpolating between their perplexities while overcoming their respective limitations. Unlike prior work, which uses transformers with bidirectional attention as MDM denoisers, we exploit the connection between MDMs and Any-Order autoregressive models and adopt causal attention. This design lets us compute the exact likelihood of MDMs for the first time and, crucially, enables us to introduce KV caching for MDMs while preserving parallel generation for the first time, significantly improving inference efficiency. Combined with an optimized sampling schedule, Eso-LMs establish a new state of the art on the speed-quality Pareto frontier for unconditional generation. We provide the code, model checkpoints, and the video tutorial on the project page: https://s-sahoo.com/Eso-LMs.

cs.CL↗

arXiv2025

FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion

Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream 7B, LLaDA 8B) suffer from slow inference. While they match the quality of similarly sized autoregressive (AR) models (e.g., Qwen2.5 7B, Llama3 8B), their iterative denoising requires multiple full-sequence forward passes, resulting in high computational costs and latency, particularly for long input prompts and long-context scenarios. Furthermore, parallel token generation introduces token incoherence problems, and current sampling heuristics suffer from significant quality drops with decreasing denoising steps. We address these limitations with two training-free techniques. First, we propose FreeCache, a Key-Value (KV) approximation caching technique that reuses stable KV projections across denoising steps, effectively reducing the computational cost of DLM inference. Second, we introduce Guided Diffusion, a training-free method that uses a lightweight pretrained autoregressive model to supervise token unmasking, dramatically reducing the total number of denoising iterations without sacrificing quality. We conduct extensive evaluations on open-source reasoning benchmarks, and our combined methods deliver an average of 12.14x end-to-end speedup across various tasks with negligible accuracy degradation. For the first time, diffusion language models achieve a comparable and even faster latency as the widely adopted autoregressive models. Our work successfully paved the way for scaling up the diffusion language model to a broader scope of applications across different domains.

cs.CL↗

arXiv2025

SplitReason: Learning To Offload Reasoning

Reasoning in large language models (LLMs) tends to produce substantially longer token generation sequences than simpler language modeling tasks. This extended generation length reflects the multi-step, compositional nature of reasoning and is often correlated with higher solution accuracy. From an efficiency perspective, longer token generation exacerbates the inherently sequential and memory-bound decoding phase of LLMs. However, not all parts of this expensive reasoning process are equally difficult to generate. We leverage this observation by offloading only the most challenging parts of the reasoning process to a larger, more capable model, while performing most of the generation with a smaller, more efficient model; furthermore, we teach the smaller model to identify these difficult segments and independently trigger offloading when needed. To enable this behavior, we annotate difficult segments across 18k reasoning traces from the OpenR1-Math-220k chain-of-thought (CoT) dataset. We then apply supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to a 1.5B-parameter reasoning model, training it to learn to offload the most challenging parts of its own reasoning process to a larger model. This approach improves AIME24 reasoning accuracy by 24% and 28.3% while offloading 1.35% and 5% of the generated tokens respectively. We open-source our SplitReason model, data, code and logs.

cs.CL↗

arXiv2025

xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent studies attempt to share KV-Cache across layers, but these approaches either require expensive pretraining or rely on per-token cross-layer cosine similarity that is often limited in practice. We show, via Centered Kernel Alignment (CKA), that the dominant singular vectors of KV-Cache are well aligned across layers. Motivated by this observation, we propose xKV, a post-training compression method that jointly factorizes grouped-layer KV-Cache into a shared low-rank subspace, substantially reducing KV-Cache memory. Across widely used LLMs, xKV achieves up to 8x KV-Cache compression while preserving accuracy on long-context tasks and in multi-turn settings. To further improve efficiency, we introduce Selective Reconstruction (SR) at decode time. Combined with SR, xKV achieves up to 4.23x end-to-end speedup over the full attention baseline, and surpasses notable baselines with 30% higher throughput under a similar accuracy level. Overall, xKV provides a plug-and-play approach to reduce both memory and latency for long-context LLM inference. Our code is publicly available at: https://github.com/abdelfattah-lab/xKV.

cs.CL↗

arXiv2025

TokenButler: Token Importance is Predictable

Large Language Models (LLMs) rely on the Key-Value (KV) Cache to store token history, enabling efficient decoding of tokens. As the KV-Cache grows, it becomes a major memory and computation bottleneck. However, there is an opportunity to alleviate this bottleneck, prior research has shown that only a small subset of tokens contribute meaningfully to each decoding step. A key challenge in finding these critical tokens is that they are dynamic, and heavily input query-dependent. Existing methods either risk quality by evicting tokens permanently, or retain the full KV-Cache but rely on retrieving chunks of tokens and many existing KV-Cache sparsity methods rely on inaccurate proxies for token importance. To address these limitations, we introduce TokenButler, a high-granularity, query-aware predictor that learns to identify these critical tokens. TokenButler predicts low-dimensional importance queries at a fixed depth stride, and combines them with a learned projection of the real KV-cache keys to score tokens cheaply, enabling dynamic per-token selection under a fixed budget while preserving the full KV cache. We train TokenButler by distilling the model's masked causal attention distributions, optimizing a lightweight predictor with minimal parameter overhead. We evaluate TokenButler on a novel synthetic small-context co-referential retrieval task, demonstrating near-oracle accuracy where existing methods fail. Furthermore, TokenButler achieves competitive or superior performance on long-context benchmarks (RULER, LongBench), up to $\approx1.6\times$ on-GPU speedup using our proposed *prediction interval with neighbor fetching* that amortizes predictor cost while maintaining accuracy within $\approx$1.1\%, and up to 7.6$\times$ reduction in latency compared to Dense Attention with CPU offloading. Code is available: https://github.com/abdelfattah-lab/TokenButler

cs.CL↗

arXiv2025

SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs

Large language models have high compute, latency, and memory requirements. While specialized accelerators such as GPUs and TPUs typically run these workloads, CPUs are more widely available and consume less energy. Accelerating LLMs with CPUs enables broader AI access at a lower cost and power consumption. This acceleration potential for CPUs is especially relevant during the memory-bound decoding stage of LLM inference, which processes one token at a time and is becoming increasingly utilized with reasoning models. We utilize Advanced Matrix Extensions (AMX) support on the latest Intel CPUs together with unstructured sparsity to achieve a $1.42 \times$ reduction in end-to-end latency compared to the current PyTorch implementation by applying our technique in linear layers. We provide a set of open-source customized sparse kernels that can speed up any PyTorch model by automatically replacing all linear layers with our custom sparse implementation. Furthermore, we demonstrate for the first time the use of unstructured sparsity in the attention computation achieving a $1.14 \times$ speedup over the current systems without compromising accuracy. Code: https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SparAMX

cs.LG↗

arXiv2024

Attamba: Attending To Multi-Token States

When predicting the next token in a sequence, vanilla transformers compute attention over all previous tokens, resulting in quadratic scaling of compute with sequence length. State-space models compress the entire sequence of tokens into a fixed-dimensional representation to improve efficiency, while other architectures achieve sub-quadratic complexity via low-rank projections or sparse attention patterns over the sequence. In this paper, we introduce Attamba, a novel architecture that uses state-space models to compress chunks of tokens and applies attention on these compressed key-value representations. We find that replacing key and value projections in a transformer with SSMs can improve model quality and enable flexible token chunking, resulting in 24% improved perplexity with transformer of similar KV-Cache and attention footprint, and ~4 times smaller KV-Cache and Attention FLOPs for 5% perplexity trade-off. Attamba can perform attention on chunked-sequences of variable length, enabling a smooth transition between quadratic and linear scaling, offering adaptable efficiency gains.

cs.LG↗

arXiv2024

ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models

The high power consumption and latency-sensitive deployments of large language models (LLMs) have motivated efficiency techniques like quantization and sparsity. Contextual sparsity, where the sparsity pattern is input-dependent, is crucial in LLMs because the permanent removal of attention heads or neurons from LLMs can significantly degrade accuracy. Prior work has attempted to model contextual sparsity using neural networks trained to predict activation magnitudes, which can be used to dynamically prune structures with low predicted activation magnitude. In this paper, we look beyond magnitude-based pruning criteria to assess attention head and neuron importance in LLMs. We develop a novel predictor called ShadowLLM, which can shadow the LLM behavior and enforce better sparsity patterns, resulting in over 15% improvement in end-to-end accuracy compared to prior methods. In addition, ShadowLLM achieves up to a 20% speed-up over the state-of-the-art DejaVu framework. These enhancements are validated on Llama-2 and OPT models with up to 30 billion parameters. Our code is available at \href{https://github.com/abdelfattah-lab/shadow_llm/}{ShadowLLM}.

cs.LG↗

arXiv2024

Radial Networks: Dynamic Layer Routing for High-Performance Large Language Models

Large language models (LLMs) often struggle with strict memory, latency, and power demands. To meet these demands, various forms of dynamic sparsity have been proposed that reduce compute on an input-by-input basis. These methods improve over static methods by exploiting the variance across individual inputs, which has steadily grown with the exponential increase in training data. Yet, the increasing depth within modern models, currently with hundreds of layers, has opened opportunities for dynamic layer sparsity, which skips the computation for entire layers. In this work, we explore the practicality of layer sparsity by profiling residual connections and establish the relationship between model depth and layer sparsity. For example, the residual blocks in the OPT-66B model have a median contribution of 5% to its output. We then take advantage of this dynamic sparsity and propose Radial Networks, which perform token-level routing between layers guided by a trained router module. These networks can be used in a post-training distillation from sequential networks or trained from scratch to co-learn the router and layer weights. They enable scaling to larger model sizes by decoupling the number of layers from the dynamic depth of the network, and their design allows for layer reuse. By varying the compute token by token, they reduce the overall resources needed for generating entire sequences. Overall, this leads to larger capacity networks with significantly lower compute and serving costs for large language models.

cs.CL↗

arXiv2024

On Latency Predictors for Neural Architecture Search

Efficient deployment of neural networks (NN) requires the co-optimization of accuracy and latency. For example, hardware-aware neural architecture search has been used to automatically find NN architectures that satisfy a latency constraint on a specific hardware device. Central to these search algorithms is a prediction model that is designed to provide a hardware latency estimate for a candidate NN architecture. Recent research has shown that the sample efficiency of these predictive models can be greatly improved through pre-training on some \textit{training} devices with many samples, and then transferring the predictor on the \textit{test} (target) device. Transfer learning and meta-learning methods have been used for this, but often exhibit significant performance variability. Additionally, the evaluation of existing latency predictors has been largely done on hand-crafted training/test device sets, making it difficult to ascertain design features that compose a robust and general latency predictor. To address these issues, we introduce a comprehensive suite of latency prediction tasks obtained in a principled way through automated partitioning of hardware device sets. We then design a general latency predictor to comprehensively study (1) the predictor architecture, (2) NN sample selection methods, (3) hardware device representations, and (4) NN operation encoding schemes. Building on conclusions from our study, we present an end-to-end latency predictor training strategy that outperforms existing methods on 11 out of 12 difficult latency prediction tasks, improving latency prediction by 22.5\% on average, and up to to 87.6\% on the hardest tasks. Focusing on latency prediction, our HW-Aware NAS reports a $5.8\times$ speedup in wall-clock time. Our code is available on \href{https://github.com/abdelfattah-lab/nasflat_latency}{https://github.com/abdelfattah-lab/nasflat\_latency}.

cs.LG↗

arXiv2024

Encodings for Prediction-based Neural Architecture Search

Predictor-based methods have substantially enhanced Neural Architecture Search (NAS) optimization. The efficacy of these predictors is largely influenced by the method of encoding neural network architectures. While traditional encodings used an adjacency matrix describing the graph structure of a neural network, novel encodings embrace a variety of approaches from unsupervised pretraining of latent representations to vectors of zero-cost proxies. In this paper, we categorize and investigate neural encodings from three main types: structural, learned, and score-based. Furthermore, we extend these encodings and introduce \textit{unified encodings}, that extend NAS predictors to multiple search spaces. Our analysis draws from experiments conducted on over 1.5 million neural network architectures on NAS spaces such as NASBench-101 (NB101), NB201, NB301, Network Design Spaces (NDS), and TransNASBench-101. Building on our study, we present our predictor \textbf{FLAN}: \textbf{Fl}ow \textbf{A}ttention for \textbf{N}AS. FLAN integrates critical insights on predictor design, transfer learning, and \textit{unified encodings} to enable more than an order of magnitude cost reduction for training NAS accuracy predictors. Our implementation and encodings for all neural networks are open-sourced at \href{https://github.com/abdelfattah-lab/flan_nas}{https://github.com/abdelfattah-lab/flan\_nas}.

cs.LG↗

arXiv2023

Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search

Many hardware-aware neural architecture search (NAS) methods have been developed to optimize the topology of neural networks (NN) with the joint objectives of higher accuracy and lower latency. Recently, both accuracy and latency predictors have been used in NAS with great success, achieving high sample efficiency and accurate modeling of hardware (HW) device latency respectively. However, a new accuracy predictor needs to be trained for every new NAS search space or NN task, and a new latency predictor needs to be additionally trained for every new HW device. In this paper, we explore methods to enable multi-task, multi-search-space, and multi-HW adaptation of accuracy and latency predictors to reduce the cost of NAS. We introduce a novel search-space independent NN encoding based on zero-cost proxies that achieves sample-efficient prediction on multiple tasks and NAS search spaces, improving the end-to-end sample efficiency of latency and accuracy predictors by over an order of magnitude in multiple scenarios. For example, our NN encoding enables multi-search-space transfer of latency predictors from NASBench-201 to FBNet (and vice-versa) in under 85 HW measurements, a 400$\times$ improvement in sample efficiency compared to a recent meta-learning approach. Our method also improves the total sample efficiency of accuracy predictors by over an order of magnitude. Finally, we demonstrate the effectiveness of our method for multi-search-space and multi-task accuracy prediction on 28 NAS search spaces and tasks.

cs.LG↗

arXiv2022

EZNAS: Evolving Zero Cost Proxies For Neural Architecture Scoring

Neural Architecture Search (NAS) has significantly improved productivity in the design and deployment of neural networks (NN). As NAS typically evaluates multiple models by training them partially or completely, the improved productivity comes at the cost of significant carbon footprint. To alleviate this expensive training routine, zero-shot/cost proxies analyze an NN at initialization to generate a score, which correlates highly with its true accuracy. Zero-cost proxies are currently designed by experts conducting multiple cycles of empirical testing on possible algorithms, datasets, and neural architecture design spaces. This experimentation lowers productivity and is an unsustainable approach towards zero-cost proxy design as deep learning use-cases diversify in nature. Additionally, existing zero-cost proxies fail to generalize across neural architecture design spaces. In this paper, we propose a genetic programming framework to automate the discovery of zero-cost proxies for neural architecture scoring. Our methodology efficiently discovers an interpretable and generalizable zero-cost proxy that gives state of the art score-accuracy correlation on all datasets and search spaces of NASBench-201 and Network Design Spaces (NDS). We believe that this research indicates a promising direction towards automatically discovering zero-cost proxies that can work across network architecture design spaces, datasets, and tasks.

cs.LG↗

arXiv2021

Enabling NAS with Automated Super-Network Generation

Recent Neural Architecture Search (NAS) solutions have produced impressive results training super-networks and then deriving subnetworks, a.k.a. child models that outperform expert-crafted models from a pre-defined search space. Efficient and robust subnetworks can be selected for resource-constrained edge devices, allowing them to perform well in the wild. However, constructing super-networks for arbitrary architectures is still a challenge that often prevents the adoption of these approaches. To address this challenge, we present BootstrapNAS, a software framework for automatic generation of super-networks for NAS. BootstrapNAS takes a pre-trained model from a popular architecture, e.g., ResNet- 50, or from a valid custom design, and automatically creates a super-network out of it, then uses state-of-the-art NAS techniques to train the super-network, resulting in subnetworks that significantly outperform the given pre-trained model. We demonstrate the solution by generating super-networks from arbitrary model repositories and make available the resulting super-networks for reproducibility of the results.

cs.LG↗