Deterministic Differentiable Structured Pruning for Large Language Models

Abstract

Structured pruning reduces LLM inference cost by removing low-importance architectural components. This can be viewed as learning a multiplicative gate for each component under an $\ell_0$ sparsity constraint. Due to the discreteness of the $\ell_0$ norm, prior work typically adopts stochastic hard-concrete relaxations to enable differentiable optimization; however, this stochasticity can introduce a train--test mismatch when sampled masks are discretized for deployment and restricting masks to a bounded, near-binary range. To address this, we propose Deterministic Differentiable Pruning (DDP), a mask-only optimization method that eliminates stochasticity by directly optimizing a deterministic soft surrogate of the discrete $\ell_0$ objective. Compared with prior approaches, DDP offers greater expressiveness, reduced train--test mismatch, and faster convergence. We apply our method to several dense and MoE models, including Qwen3-32B and Qwen3-30B-A3B, achieving a performance loss as small as 1\% on downstream tasks while outperforming previous methods at 20\% sparsity. We further demonstrate end-to-end inference speedups in realistic deployment settings with vLLM.