Discrete diffusion language models (dLLMs) offer an attractive alternative to autoregressive generation by updating multiple tokens in parallel, but their inference efficiency is still limited by the cost of safely committing tentative predictions. In particular, speculative decoding for dLLMs is challenging because speculative tokens within the same diffusion block may depend on one another, making aggressive acceptance prone to error propagation and strict verification computationally expensive. We present PV-Decoding, a confidence-driven speculative decoding framework with progressive verification for block diffusion inference. PV-Decoding partitions masked positions into directly decoded tokens, speculative tokens, and unresolved tokens using two confidence thresholds, and then verifies speculative tokens with progressively stronger policies, including single-batch, dual-batch, and multi-batch verification. This design exposes a practical accuracy–efficiency trade-off: weaker verification minimizes overhead, whereas stronger verification improves acceptance precision and robustness. Experiments on three diffusion language models across GSM8K, MBPP, and HumanEval show that PV-Decoding reduces sequential model forward passes (MFPs) by 8%–37% relative to confidence-based decoding, while keeping the largest observed accuracy drop to 1.3%. On Dream-7B-Instruct/GSM8K, PV-Decoding (1-batch) and PV-Decoding (2-batch) improve throughput by 7.0%–13.6% under the same hardware budget, whereas PV-Decoding (multi-batch) is slower under the current runtime. These results suggest that confidence-guided speculation with structured verification is a practical path toward efficient and reliable dLLM inference.

With the increasing size of large language models, layer pruning has gained increased attention as a hardware-friendly approach for model compression. However, existing layer pruning methods struggle to simultaneously address key practical deployment challenges, including performance degradation, high training costs, and limited acceleration. To overcome these limitations, we propose E³-Pruner, a task-Effective, training-Economical and inference-Efficient layer pruning framework. E³-Pruner introduces two key innovations: (1) a differentiable mask optimization method using a Gumbel-TopK sampler, enabling efficient and precise pruning mask search; and (2) an entropy-aware adaptive knowledge distillation strategy that enhances task performance. Extensive experiments over diverse model architectures and benchmarks demonstrate the superiority of our method over state-of-the-art approaches. Notably, E³-Pruner achieves 96% accuracy, a mere 0.8% drop from the original model (96.8%) on MATH-500 when pruning 25% layers of Qwen3-32B, outperforming existing SOTA (95%), with a 1.33× inference speedup by consuming merely 0.5B tokens (0.5% of the post-training data volume).

Judge Decoding accelerates LLM inference by relaxing the strict verification of Speculative Decoding, yet it typically relies on expensive and noisy supervision. In this work, we revisit this paradigm from first principles, revealing that the “criticality” scores learned via costly supervision are intrinsically encoded in the draft-target distributional divergence. We theoretically prove a structural correspondence between learned linear judges and Kullback-Leibler (KL) divergence, demonstrating they rely on the same underlying logit primitives. Guided by this, we propose a simple, training-free verification mechanism based on KL divergence. Extensive experiments across reasoning and coding benchmarks show that our method matches or outperforms complex trained judges (e.g., AutoJudge), offering superior robustness to domain shifts and eliminating the supervision bottleneck entirely. Code is available at https://github.com/sunshy-1/JuDi.

Scaling large language models (LLMs) improves performance but significantly increases inference costs, with feed-forward networks (FFNs) consuming the majority of computational resources. While Mixture-of-Experts (MoE) architectures can reduce this cost through sparse activation, restructuring existing dense models into MoEs typically requires extensive retraining on hundreds of billions of tokens.We propose an analytical post-training framework that rapidly restructures FFNs into sparse MoE architectures using only a small calibration dataset. The method analyzes neuron activation patterns to partition neurons into always-active shared experts and conditionally activated routed experts, then constructs a router analytically from representative neuron statistics, enabling immediate deployment or optional lightweight fine-tuning. This approach applies both to dense models and recursively to existing MoE models for hierarchical sparsity.Experiments demonstrate up to 1.17× speedup in compute-bound scenarios with only minutes of processing and 2k-sample fine-tuning, outperforming methods requiring orders of magnitude more resources.

Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms being proposed, they mostly focus on integer quantization, while their applicability and behavior under MXFP formats remain largely unexplored. To address this gap, this work conducts a systematic investigation of PTQ under MXFP formats, encompassing over 7 PTQ algorithms, 15 evaluation benchmarks, and 3 LLM families. The key findings include: 1) MXFP8 consistently achieves near-lossless performance, while MXFP4 introduces substantial accuracy degradation and remains challenging; 2) PTQ effectiveness under MXFP depends strongly on format compatibility, with some algorithmic paradigms being consistently more effective than others; 3) PTQ performance exhibits highly consistent trends across model families and modalities, in particular, quantization sensitivity is dominated by the language model rather than the vision encoder in multimodal LLMs; 4) The scaling factor of quantization is a critical error source in MXFP4, and a simple pre-scale optimization strategy can significantly mitigate its impact. Together, these results provide practical guidance on adapting existing PTQ methods to MXFP quantization.

As LLMs scale, low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. In this work, we evaluate HiFloat (HiF8 and HiF4), a family of formats tailored for Ascend NPUs. Through rigorous comparison across weight-activation and KV-cache tasks, we provide three key insights: (1) INT8 suits narrow-range data, while floating-point formats excel with high-variance data; (2) in 4-bit regimes, HiF4’s hierarchical scaling prevents the accuracy collapse seen in integer formats; and (3) HiFloat is fully compatible with state-of-the-art post-training quantization frameworks. Overall, HiFloat provides a solution for high-efficiency LLM inference on NPUs.

Test-Time Scaling (TTS) has proven effective in improving the performance of Large Language Models (LLMs) during inference. However, existing research has overlooked the efficiency of TTS from a latency-sensitive perspective. Through a latency-aware evaluation of representative TTS methods, we demonstrate that a compute-optimal TTS does not always result in the lowest latency in scenarios where latency is critical. To address this gap and achieve latency-optimal TTS, we propose two key approaches by optimizing the concurrency configurations: (1) branch-wise parallelism, which leverages multiple concurrent inference branches, and (2) sequence-wise parallelism, enabled by speculative decoding. By integrating these two approaches and allocating computational resources properly to each, our latency-optimal TTS enables a 32B model to reach 82.3% accuracy on MATH-500 within 1 minute and a smaller 3B model to achieve 72.4% within 10 seconds. Our work emphasizes the importance of latency-aware TTS and demonstrates its ability to deliver both speed and accuracy in latency-sensitive scenarios.

This paper presents the submission of Huawei Translation Services Center (HW-TSC) to WMT 2022 Efficiency Shared Task. For this year’s task, we still apply sentence-level distillation strategy to train small models with different configurations. Then, we integrate the average attention mechanism into the lightweight RNN model to pursue more efficient decoding. We tried adding a retrain step to our 8-bit and 4-bit models to achieve a balance between model size and quality. We still use Huawei Noah’s Bolt for INT8 inference and 4-bit storage. Coupled with Bolt’s support for batch inference and multi-core parallel computing, we finally submit models with different configurations to the CPU latency and throughput tracks to explore the Pareto frontiers.