The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable. We test that assumption: holding the checkpoint, prompts, hardware, inference engine, decoding, and quantization configuration fixed, we swap only the INT8 linear kernel (CUTLASS versus Triton) inside vLLM. At 1.7B each arm reproduces itself bit-for-bit across cold restarts, yet the arms agree on no sequence in any end-to-end comparison we ran (0/8, 0/16, and 0/64). What makes this more than a benchmark discrepancy is an integer alibi: for shared INT8 operands under a verified no-overflow bound, the INT32 dot product is exact and order-independent, so the accumulator cannot be the source of any difference. Feeding both kernels identical operands from every linear layer of Qwen3-1.7B and 8B (196 and 252 layers), we find bit-identical outputs under power-of-two scales, confirming a pinned prediction list 196/196 and 252/252 (pre-registered at 1.7B, pinned but not blind at 8B), and observed differences of at most one bfloat16 spacing under the checkpoints' real scales. This localizes the divergence to scale application and output rounding after the exact accumulator. Applied as a probe checkpoint, the same intervention restores end-to-end bitwise agreement (8/8 and 16/16 sequences). Cross-implementation FP8 GEMM shows a different signature: both the prevalence and the magnitude of differences grow with reduction depth, while the INT8 fraction stays at parts per million and within one spacing over a 64x range of K. Teacher-forced replay ties layers to tokens: flips concentrate at small logit margins, which predict flip risk with ROC-AUC 0.94 on 16,384 positions. We will release the pre-registration, per-layer predictions, manifests with kernel-selection evidence, and a conformance procedure that turns these controls into a concrete check for kernel interchangeability.

Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models

Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a per-instance oracle. Recent analysis shows that test-time resampling can recover per-instance selection headroom that no single-commit router captures; however, that guarantee holds only under an idealized oracle equipped with correctness labels and an unconstrained budget, neither of which a deployed system has. To the best of our knowledge, no previous work treats resampling the committed model and rerouting to an alternative model as competing uses of a single per-query cost budget. Therefore, this work formulates budget-aware test-time model selection: given a per-query budget and an imperfect verifier, allocate each unit of budget between resampling and rerouting so that expected correctness is maximized. An online resample-or-reroute (RoR) allocation policy driven by estimated marginal correctness per unit cost is proposed, and its behavior is grounded in the recoverability asymmetry between selection and sampling. Replay experiments on newly regenerated multi-draw correctness tensors from an eleven-model open-weight pool over four benchmarks of differing difficulty show that the proposed RoR policy attains a favorable cost-quality Pareto front relative to single-route, one-commit-router, budget-aware best-of-K, cascade, and random-allocation baselines for the tested pools, with the largest gains on the most heterogeneous benchmark; an ablation further shows the gains are verifier-gated, shrinking as verifier quality degrades, and robustness replays under a provider price vector and a label-free agreement verifier delineate where the conclusions carry over.

How Much of the Routing Gap Is Real? Decomposing the Router-to-Oracle Gap into Reproducible Specialist Advantage and Single-Draw Label Noise

Routing among large language models (LLMs) promises better quality at lower cost, motivated by the reported gap between learned routers and a per-instance oracle. But that oracle is computed from a single correctness label per (query, model), so under stochastic decoding it is one Bernoulli draw, not a reproducible property. We recast the question structurally: the expected per-instance oracle decomposes as $O^{\exp}=O^{\mathrm{repro}}+Δ$, into reproducible single-commit headroom $O^{\mathrm{repro}}$ and a non-negative single-commit selection floor $Δ$. Our main result is a recoverability asymmetry: this floor is closed by no single-commit router, yet is recovered by test-time sampling -- best-of-$K$ on the committed model, at the oracle's own budget, dominates the independent-pool single-draw oracle. The cap needs no cross-model independence; we prove it with the exact decomposition and noise-share bounds that shrink as the budget grows. The procedure adds no new router, only resampling. The floor's magnitude is a prospective, conservative localization, not an audit: our primary target LLMRouterBench (33 models, 391,645 instances) defines its oracle as a per-query union over single $T=0.2$ generations -- by construction a union of stochastic single draws. Since $O^{\mathrm{repro}}$ is non-identifiable from the released $k=1$ matrix, we estimate the noise share by fresh $k\ge20$ resampling under one-sided, dependence- and guessing-floor-corrected bounds, recasting 'model-recall failure' as thin-support union inflation. On a controlled open-model re-generation, single-draw noise is a substantial minority of the gap -- larger on an unsaturated benchmark, approaching half on the hardest queries where no model is reliable -- while the majority remains recoverable specialist advantage. We release a multi-sample oracle evaluation protocol for routing benchmarks.

Dual Engines of Thoughts: A Depth-Breadth Integration Framework for Open-Ended Analysis

We propose the Dual Engines of Thoughts (DEoT), an analytical framework for comprehensive open-ended reasoning. While traditional reasoning frameworks primarily focus on finding "the best answer" or "the correct answer" for single-answer problems, DEoT is specifically designed for "open-ended questions," enabling both broader and deeper analytical exploration. The framework centers on three key components: a Base Prompter for refining user queries, a Solver Agent that orchestrates task decomposition, execution, and validation, and a Dual-Engine System consisting of a Breadth Engine (to explore diverse impact factors) and a Depth Engine (to perform deep investigations). This integrated design allows DEoT to balance wide-ranging coverage with in-depth analysis, and it is highly customizable, enabling users to adjust analytical parameters and tool configurations based on specific requirements. Experimental results show that DEoT excels in addressing complex, multi-faceted questions, achieving a total win rate of 77-86% compared to existing reasoning models, thus highlighting its effectiveness in real-world applications.

Plan2Align: Predictive Planning Based Test-Time Preference Alignment in Paragraph-Level Machine Translation

Machine Translation (MT) has been predominantly designed for sentence-level translation using transformer-based architectures. While next-token prediction based Large Language Models (LLMs) demonstrate strong capabilities in long-text translation, non-extensive language models often suffer from omissions and semantic inconsistencies when processing paragraphs. Existing preference alignment methods improve sentence-level translation but fail to ensure coherence over extended contexts due to the myopic nature of next-token generation. We introduce Plan2Align, a test-time alignment framework that treats translation as a predictive planning problem, adapting Model Predictive Control to iteratively refine translation outputs. Experiments on WMT24 Discourse-Level Literary Translation show that Plan2Align significantly improves paragraph-level translation, achieving performance surpassing or on par with the existing training-time and test-time alignment methods on LLaMA-3.1 8B.