Hasil untuk "Speculative philosophy"

Mohamad Zbib, Mohamad Bazzi, Ammar Mohanna et al.

Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In practice, however, draft models are usually trained on broad generic corpora, which leaves it unclear how much speculative decoding quality depends on the draft training distribution. We study this question with lightweight HASS and EAGLE-2 drafters trained on MathInstruct, ShareGPT, and mixed-data variants, evaluated on MT-Bench, GSM8K, MATH-500, and SVAMP. Measured by acceptance length, task-specific training yields clear specialization: MathInstruct-trained drafts are strongest on reasoning benchmarks, while ShareGPT-trained drafts are strongest on MT-Bench. Mixed-data training improves robustness, but larger mixtures do not dominate across decoding temperatures. We also study how to combine specialized drafters at inference time. Naive checkpoint averaging performs poorly, whereas confidence-based routing improves over single-domain drafts and merged-tree verification yields the highest acceptance length overall for both backbones. Finally, confidence is a more useful routing signal than entropy: rejected tokens tend to have higher entropy, but confidence produces much clearer benchmark-level routing decisions. These results show that speculative decoding quality depends not only on draft architecture, but also on the match between draft training data and downstream workload, and that specialized drafters are better combined at inference time than in weight space.

Guang Huang, Zeyi Wen

Speculative Decoding (SD) has emerged as a premier technique for accelerating Large Language Model (LLM) inference by decoupling token generation into rapid drafting and parallel verification. While recent advancements in self-speculation and lookahead decoding have successfully minimized drafting overhead, they have shifted the primary performance bottleneck to the verification phase. Since verification requires a full forward pass of the target model, it remains strictly memory-bandwidth bound, fundamentally limiting the maximum achievable speedup.In this paper, we introduce \textbf{Quasar} (\textbf{Qua}ntized \textbf{S}elf-speculative \textbf{A}cceleration for \textbf{R}apid Inference), a novel, training-free framework designed to overcome this "memory wall" by employing low-bit quantization specifically for the verification stage. Our empirical analysis reveals that while aggressive structural pruning significantly degrades verification accuracy, quantization-based verification preserves the logit distribution with high fidelity while effectively halving memory traffic. Extensive experiments on state-of-the-art models (e.g., OpenPangu and Qwen3) demonstrate that Quasar maintains a speculative acceptance length comparable to full-precision methods while achieving a $1.28\times$ improvement in end-to-end throughput. Being orthogonal to existing drafting strategies, Quasar offers a generic and efficient pathway to accelerate the verification leg of speculative execution. Code is available at https://github.com/Tom-HG/Quasar.

Jonathan Baumann, Yonghyun Kim, Yan Farba et al.

This paper introduces Triosecuris, a formally verified defense against Spectre BTB, RSB, and PHT that combines CET-style hardware-assisted control-flow integrity with compiler-inserted speculative load hardening (SLH). Triosecuris is based on the novel observation that in the presence of CET-style protection, we can precisely detect BTB misspeculation for indirect calls and RSB misspeculation for returns and set the SLH misspeculation flag. We formalize Triosecuris as a transformation in Rocq and provide a machine-checked proof that it achieves relative security: any transformed program running with speculation leaks no more than what the source program leaks without speculation. This strong security guarantee applies to arbitrary programs, even those not following the cryptographic constant-time programming discipline.

Daniel Benevides Soares

O ciúme é um dos temas do romance Dom Casmurro, de Machado de Assis. Esse é um dos elementos que podem proporcionar uma leitura filosófica do romance. Como o ciumento Bentinho é um advogado, o tema da consideração filosófica sobre o direito se mostra como outro liame possível entre obra machadiana e a filosofia. Investigando esse laço pela filosofia do direito de Eric Weil, propomos um trabalho constando de duas partes. Na primeira apresentamos as linhas gerais da filosofia do direito weiliana contida, mormente, na sua obra Filosofia política. Em seguida propomos uma aplicação dos conceitos weilianos a algumas situações descritas no romance Dom Casmurro. Nas considerações finais incluímos um balanço da discussão.

Bo Fu, Leo Tenenbaum, David Adler et al.

In recent years, several hardware-based countermeasures proposed to mitigate Spectre attacks have been shown to be insecure. To enable the development of effective secure speculation countermeasures, we need easy-to-use tools that can automatically test their security guarantees early-on in the design phase to facilitate rapid prototyping. This paper develops AMuLeT, the first tool capable of testing secure speculation countermeasures for speculative leakage early in their design phase in simulators. Our key idea is to leverage model-based relational testing tools that can detect speculative leaks in commercial CPUs, and apply them to micro-architectural simulators to test secure speculation defenses. We identify and overcome several challenges, including designing an expressive yet realistic attacker observer model in a simulator, overcoming the slow simulation speed, and searching the vast micro-architectural state space for potential vulnerabilities. AMuLeT speeds up test throughput by more than 10x compared to a naive design and uses techniques to amplify vulnerabilities to uncover them within a limited test budget. Using AMuLeT, we launch for the first time, a systematic, large-scale testing campaign of four secure speculation countermeasures from 2018 to 2024--InvisiSpec, CleanupSpec, STT, and SpecLFB--and uncover 3 known and 6 unknown bugs and vulnerabilities, within 3 hours of testing. We also show for the first time that the open-source implementation of SpecLFB is insecure.

Clara Mohri, Haim Kaplan, Tal Schuster et al.

Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft model to propose tokens that the larger target model verifies in parallel. In practice, however, there may exist a set of potential draft models- ranging from faster but less inaccurate, to slower yet more reliable. We introduce Hierarchical Speculative Decoding (HSD), an algorithm that stacks these draft models into a hierarchy, where each model proposes tokens, and the next larger model verifies them in a single forward pass, until finally the target model verifies tokens. We derive an expression for the expected latency of any such hierarchy and show that selecting the latency-optimal hierarchy can be done in polynomial time. Empirically, HSD gives up to 1.2x speed-up over the best single-draft baseline, demonstrating the practicality of our algorithm in reducing generation latency beyond previous techniques.

Weilin Zhao, Tengyu Pan, Xu Han et al.

Speculative sampling has emerged as an important technique for accelerating the auto-regressive generation process of large language models (LLMs) by utilizing a draft-then-verify mechanism to produce multiple tokens per forward pass. While state-of-the-art speculative sampling methods use only a single layer and a language modeling (LM) head as the draft model to achieve impressive layer compression, their efficiency gains are substantially reduced for large-vocabulary LLMs, such as Llama-3-8B with a vocabulary of 128k tokens. To address this, we present FR-Spec, a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression. By constraining the draft search to a frequency-prioritized token subset, our method reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution. Experiments across multiple datasets demonstrate an average of 1.12$\times$ speedup over the state-of-the-art speculative sampling method EAGLE-2. Code available at https://github.com/thunlp/FR-Spec.

Jinbin Zhang, Nasib Ullah, Erik Schultheis et al.

Speculative decoding accelerates LLM inference by letting a small drafter propose multiple tokens which a large target model verifies once per speculation step. As vocabularies scale past 10e5 tokens,verification cost in the target model is largely unchanged, but the drafter can become bottlenecked by its O(|V|d) output projection. Recent approaches (e.g., FR-Spec, VocabTrim) mitigate this by restricting drafting to a fixed, frequency-ranked shortlist; however, such static truncation is corpus-dependent and suppresses rare or domain-specific tokens, reducing acceptance and limiting speedups. We propose DynaSpec, a context-dependent dynamic shortlisting mechanism for large-vocabulary speculative decoding. DynaSpec trains lightweight meta-classifiers that route each context to a small set of coarse token clusters; the union of the top-selected clusters defines the drafter's shortlist, while the target model still verifies over the full vocabulary, preserving exactness. Systems-wise, routing is overlapped with draft computation via parallel execution streams, reducing end-to-end overhead. Across standard speculative decoding benchmarks, DynaSpec consistently improves mean accepted length-recovering 98.4% of full-vocabulary performance for Llama-3-8B versus 93.6% for fixed-shortlist baselines-and achieves up to a 2.23x throughput gain compared to 1.91x for static approaches on the dataset with rare tokens.

Razvan-Gabriel Dumitru, Minglai Yang, Vikas Yadav et al.

We introduce CopySpec, a simple yet effective technique to tackle the inefficiencies LLMs face when generating responses that closely resemble previous outputs or responses that can be verbatim extracted from context. CopySpec identifies repeated sequences in the model's chat history or context and speculates that the same tokens will follow, enabling seamless copying without compromising output quality and without requiring additional GPU memory. To evaluate the effectiveness of our approach, we conducted experiments using seven LLMs and five datasets: MT-Bench, CNN/DM, GSM8K, HumanEval, and our newly created dataset, MT-Redundant. MT-Redundant, introduced in this paper, transforms the second turn of MT-Bench into a request for variations of the first turn's answer, simulating real-world scenarios where users request modifications to prior responses. Our results demonstrate significant speed-ups: up to 2.35x on CNN/DM, 3.08x on the second turn of select MT-Redundant categories, and 2.66x on the third turn of GSM8K's self-correction tasks. Importantly, we show that CopySpec integrates seamlessly with speculative decoding, yielding an average 49% additional speed-up over speculative decoding for the second turn of MT-Redundant across all eight categories. While LLMs, even with speculative decoding, suffer from slower inference as context size grows, CopySpec leverages larger contexts to accelerate inference, making it a faster complementary solution. Our code and dataset are publicly available at https://github.com/RazvanDu/CopySpec.

Yifeng Gao, Ziang Ji, Yuxuan Wang et al.

Diffusion-based Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive models, offering unique advantages through bidirectional attention and parallel generation paradigms. However, the generation results of current parallel decoding methods deviate from stepwise decoding, introducing potential performance degradation, which limits their practical deployment. To address this problem, we propose \textbf{S}elf \textbf{S}peculative \textbf{D}ecoding (SSD), a lossless inference acceleration method that leverages the dLLM itself as both speculative decoding drafter and verifier without auxiliary modules. SSD introduces a self-drafting mechanism where the model generates predictions for multiple positions, then verifies them through hierarchical verification trees in a single forward pass. Unlike traditional speculative decoding that requires separate draft models, SSD eliminates model redundancy and memory overhead by exploiting the dLLM's inherent parallel prediction capability for multiple positions. This self-speculative approach allows the model to progressively verify and accept multiple tokens in a single forward pass. Our experiments demonstrate that SSD achieves up to 3.46$\times$ speedup while keeping the output identical to stepwise decoding on open source models such as LLaDA and Dream. Code will be made publicly available on GitHub.

Haiduo Huang, Fuwei Yang, Zhenhua Liu et al.

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems constraints: the prefill stage is dominated by visual tokens whose count scales with image resolution and video length, inflating both compute and memory, especially the key-value (KV) cache. We study speculative decoding for VLMs and introduce SpecVLM, a practical system that (1) establishes a strong EAGLE-2-style baseline, EagleVLM, delivering 1.5--2.3x end-to-end speedups over full autoregressive inference, and (2) further accelerates VLM inference with an elastic visual compressor that adaptively selects among pruning, pooling, convolution, and resampler primitives to balance FLOPs/parameters and accuracy per input. To avoid costly offline distillation corpora, we propose an online-logit distillation protocol that trains the draft model with on-the-fly teacher logits and penultimate features using a combined cross-entropy and Smooth L1 objective, eliminating storage and preprocessing while remaining compute-efficient. This protocol reveals a training-time scaling effect: longer online training monotonically increases the draft model's average accepted length, improving speculative efficiency. Empirically, SpecVLM achieves additional acceleration, culminating in 2.5--2.9x end-to-end speedups within 5 epochs across LLaVA and MMMU, consistently over resolutions and task difficulties, while preserving the target model's output distribution (lossless decoding). Our code is available at https://github.com/haiduo/SpecVLM.

Ye Li, Jiahe Feng, Yuan Meng et al.

Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. The temporal complexity of embodied tasks demands a dynamic and adaptable computation mode. Static and lossy acceleration methods, such as quantization, fail to handle such dynamic embodied tasks, while speculative decoding offers a lossless and adaptive yet underexplored alternative for DP. However, it is non-trivial to address the following challenges: how to match the base model's denoising quality at lower cost under time-varying task difficulty in embodied settings, and how to dynamically and interactively adjust computation based on task difficulty in such environments. In this paper, we propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP), the first framework that enables speculative decoding for DP with temporal adaptivity. First, to handle dynamic environments where task difficulty varies over time, we distill a Transformer-based drafter to imitate the base model and replace its costly denoising calls. Second, an RL-based scheduler further adapts to time-varying task difficulty by adjusting speculative parameters to maintain accuracy while improving efficiency. Extensive experiments across diverse embodied environments demonstrate that TS-DP achieves up to 4.17 times faster inference with over 94% accepted drafts, reaching an inference frequency of 25 Hz and enabling real-time diffusion-based control without performance degradation.

Shijing Hu, Jingyang Li, Xingyu Xie et al.

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token misalignment between the training and decoding phases, limiting their performance. To address this, we propose GRIFFIN, a novel framework that incorporates a token-alignable training strategy and a token-alignable draft model to mitigate misalignment. The training strategy employs a loss masking mechanism to exclude highly misaligned tokens during training, preventing them from negatively impacting the draft model's optimization. The token-alignable draft model introduces input tokens to correct inconsistencies in generated features. Experiments on LLaMA, Vicuna, Qwen and Mixtral models demonstrate that GRIFFIN achieves an average acceptance length improvement of over 8% and a speedup ratio exceeding 7%, outperforming current speculative decoding state-of-the-art methods. Our code and GRIFFIN's draft models are released publicly in https://github.com/hsj576/GRIFFIN.

Jikai Wang, Jianchao Tan, Yuxuan Hu et al.

Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs and mixture-of-experts (MoE) models. Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding to remove substantial computational redundancy in LLMs. This work systematically adopts different sparse methods on the verification stage of the speculative decoding and identifies structured redundancy across multiple dimensions. Based on these observations, we propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost. The framework further incorporates an inter-draft token and inter-layer retrieval reuse strategy to further reduce redundant computation without introducing additional training. Extensive experiments across summarization, question answering, and mathematical reasoning datasets demonstrate that the proposed methods achieve favorable efficiency-accuracy trade-offs, while maintaining stable acceptance length.

Michał Chaberek

This article concerns the question of whether St. Thomas Aquinas can be considered a young Earth creationist. This question breaks down to three different though interrelated issues: Aquinas’s view on the origin of species, his position on the length of the six days of creation (whether they were natural days or other periods of time) and his views on the age of the earth. Each of the topics is addressed separately in the subsequent sections. The article attempts to establish Thomas’s views by his explicit statements as well as what he implies in some fragments. The conclusion presents Aquinas as a creationist with an open-ended view of the timescale of the creative events and the age of the universe.

Sophia Ho, Jinsol Park, Patrick Wang

We present CREST (Compact Retrieval-Based Speculative Decoding), a redesign of REST that allows it to be effectively "compacted". REST is a drafting technique for speculative decoding based on retrieving exact n-gram matches of the most recent n tokens generated by the target LLM from a datastore. The key idea of CREST is to only store a subset of the smallest and most common n-grams in the datastore with the hope of achieving comparable performance with less storage space. We found that storing a subset of n-grams both reduces storage space and improves performance. CREST matches REST's accepted token length with 10.6-13.5x less storage space and achieves a 16.5-17.1% higher acceptance length than REST using the same storage space on the HumanEval and MT Bench benchmarks.

Wei Zhong, Manasa Bharadwaj

Speculative decoding (SD) has attracted a significant amount of research attention due to the substantial speedup it can achieve for LLM inference. However, despite the high speedups they offer, speculative decoding methods often achieve optimal performance on high-end devices or with a substantial GPU memory overhead. Given limited memory and the necessity of quantization, a high-performing model on a high-end GPU can slow down by up to 7 times. To this end, we propose Skippy Simultaneous Speculative Decoding (or S3D), a cost-effective self-speculative SD method based on simultaneous multi-token decoding and mid-layer skipping. When compared against recent effective open-source SD systems, our method has achieved one of the top performance-memory ratios while requiring minimal architecture changes and training data. Leveraging our memory efficiency, we created a smaller yet more effective SD model based on Phi-3. It is 1.4 to 2 times faster than the quantized EAGLE model and operates in half-precision while using less VRAM.

Rohitash Chandra, Mukul Ranjan

A distinct feature of Hindu religious and philosophical text is that they come from a library of texts rather than single source. The Upanishads is known as one of the oldest philosophical texts in the world that forms the foundation of Hindu philosophy. The Bhagavad Gita is core text of Hindu philosophy and is known as a text that summarises the key philosophies of the Upanishads with major focus on the philosophy of karma. These texts have been translated into many languages and there exists studies about themes and topics that are prominent; however, there is not much study of topic modelling using language models which are powered by deep learning. In this paper, we use advanced language produces such as BERT to provide topic modelling of the key texts of the Upanishads and the Bhagavad Gita. We analyse the distinct and overlapping topics amongst the texts and visualise the link of selected texts of the Upanishads with Bhagavad Gita. Our results show a very high similarity between the topics of these two texts with the mean cosine similarity of 73%. We find that out of the fourteen topics extracted from the Bhagavad Gita, nine of them have a cosine similarity of more than 70% with the topics of the Upanishads. We also found that topics generated by the BERT-based models show very high coherence as compared to that of conventional models. Our best performing model gives a coherence score of 73% on the Bhagavad Gita and 69% on The Upanishads. The visualization of the low dimensional embeddings of these texts shows very clear overlapping among their topics adding another level of validation to our results.

Yaniv Leviathan, Matan Kalman, Yossi Matias

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any changes to the outputs, by computing several tokens in parallel. At the heart of our approach lie the observations that (1) hard language-modeling tasks often include easier subtasks that can be approximated well by more efficient models, and (2) using speculative execution and a novel sampling method, we can make exact decoding from the large models faster, by running them in parallel on the outputs of the approximation models, potentially generating several tokens concurrently, and without changing the distribution. Our method can accelerate existing off-the-shelf models without retraining or architecture changes. We demonstrate it on T5-XXL and show a 2X-3X acceleration compared to the standard T5X implementation, with identical outputs.

article Editorial

.