Diffusion Language Models (DLMs) promise highly parallel text generation, yet their practical inference speed is often bottlenecked by suboptimal decoding schedulers. Standard approaches rely on 'scattered acceptance'-committing high confidence tokens at disjoint positions throughout the sequence. This approach inadvertently fractures the Key-Value (KV) cache, destroys memory locality, and forces the model into costly, repeated repairs across unstable token boundaries. To resolve this, we present the Longest Stable Prefix (LSP) scheduler, a training-free and model-agnostic inference paradigm based on monolithic prefix absorption. In each denoising step, LSP evaluates token stability via a single forward pass, dynamically identifies a contiguous left-aligned block of stable predictions, and snaps its boundary to natural linguistic or structural delimiters before an atomic commitment. This prefix-first topology yields dual benefits: systemically, it converts fragmented KV cache updates into efficient, contiguous appends; algorithmically, it preserves bidirectional lookahead over a geometrically shrinking active suffix, drastically reducing token flip rates and denoiser calls. Extensive evaluations on LLaDA-8B and Dream-7B demonstrate that LSP accelerates inference by up to 3.4x across rigorous benchmarks including mathematical reasoning, code generation, multilingual (CJK) tasks, and creative writing while matching or slightly improving output quality. By fundamentally restructuring the commitment topology, LSP bridges the gap between the theoretical parallelism of DLMs and practical hardware efficiency.
Figures & tables
Figure 1: The iterative process of the Longest Stable Prefix (LSP) scheduler. In each step, LSP performs a single forward pass to assess the stability of predictions for the current active suffix, measured by the logit margin ( δi ). Instead of accepting scattered tokens, it atomically commits the longest contiguous prefix of tokens that meet an adaptively determined stability threshold ( τ ). As shown, the frozen prefix (green) grows monolithically, causing the active suffix (white) to shrink.
Benchmark
LLaDA-8B
Dream-7B
Full
LSP (Ours)
Full
LSP (Ours)
General Tasks
MMLU
54.1
54.2 ( 2.32 × )
67.6
66.4 ( 2.12 × )
ARC-C
83.2
83.3 ( 1.91 × )
88.1
88.0 ( 2.28 × )
Hellaswag
68.7
70.7 ( 2.18 × )
81.2
82.1 ( 2.53 × )
TruthfulQA
34.4
45.8 ( 2.29 × )
55.6
53.5 ( 1.86 × )
Table 1: Main benchmark results on LLaDA-8B and Dream-7B. We report the task-specific score (%) and the inference speedup over the ‘Full‘ baseline. LSP delivers substantial speedups while maintaining or even improving task performance.
Strategy
GSM8K Score (%)
Total Steps (Avg.)
Fixed Prefix (1 tokens)
67.1
128
Fixed Prefix (2 tokens)
66.8
64
Fixed Prefix (4 tokens)
47.6
32
Fixed Prefix (8 tokens)
19.3
16
Adaptive (LSP)
69.9
∼ 68
Table 2: Ablation on Sizing Strategy (GSM8K, LLaDA-8B). Fixed-size commitment strategies are brittle, forcing a trade-off between the number of inference steps (speed) and final accuracy. LSP’s adaptive sizing dynamically finds the most effective balance.
Method
Score (%)
Total Steps (Avg.)
Ablation on Structural Snapping
LSP w/o Snapping
67.8
∼ 50
Full LSP (Ours)
69.9
∼ 68
Ablation on Commitment Topology
Scattered-Margin
68.9
128
Full LSP (Ours)
69.9
∼ 68
Table 3: Ablation studies on core LSP components (GSM8K, LLaDA-8B). Both structural snapping and the prefix-first topology are crucial for achieving high performance. Each component is compared against the full LSP method.
Task
LSP Generation Process (Committed Prefixes per Step)
Prompt:
Natalia sold clips to 4 of her friends. She sold 8 clips to each friend. Then she bought 15 more clips. How many clips does Natalia have now?
Natalia sold 8 clips to each of her 4 friends. This means she sold a total of 4 * 8 = 32 clips. She then bought 15 more clips, so she now has 32 + 15 = 47 clips. The final answer is 47.
Prompt:
John has 12 apples. He gives half to Mary. Then Mary buys twice as many apples as she received from John. How many apples does Mary have now?
John gives half of his 12 apples to Mary, so Mary receives 12 / 2 = 6 apples. Then Mary buys twice the number she received, which is 2 * 6 = 12 apples. Mary now has her original 6 plus the 12 she bought, for a total of 6 + 12 = 18 apples. Answer: 18.
Table 4: Visualization of LSP’s monolithic prefix absorption for math reasoning (Granular View). Each colored block represents the Longest Stable Prefix atomically committed in a single step. This more detailed breakdown shows how LSP iteratively extends the solution by committing shorter, coherent chunks. The strict left-to-right, contiguous growth (light to dark green) is maintained, and commit boundaries align with natural linguistic or mathematical units (e.g., clauses, calculations), demonstrating LSP’s structural snapping in action.
Figure 2: Quantifying Repair Costs via Token Flip Rate. We measure the percentage of tokens in the active suffix that change their top prediction between consecutive diffusion steps. While the scattered baseline forces the model to constantly reconcile a fragmented context (maintaining high flip rates), LSP locks in a coherent prefix early. This stabilizes the future generation context, drastically reducing token oscillations and repair costs in the mid-to-late stages (from 14.2% down to 4.3%).
School of Computer Science and Technology, University of Science and Technology of China · Suzhou Institute of Advanced Research, University of Science and Technology of China