XMerge is a post‑training method for compressing large language models by removing entire transformer layers while preserving a standard serving architecture. It selects low‑impact blocks via cross‑axis selection and refits adjacent surviving blocks with local boundary reconstruction, requiring no task labels or fine‑tuning. Across seven Llama and Qwen backbones, XMerge outperforms five published baselines, achieving top rankings on CORE and MMLU tasks even at aggressive compression levels, and consistently avoids model collapse while improving calibration and decoding efficiency.
arXiv:2606. 02559v1 Announce Type: cross Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules.
arXiv:2609.40127v1 Announce Type: cross Abstract: Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keepin...
Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping the matrices dense, and thus efficient on standar...
arXiv:2609.15838v1 Announce Type: cross Abstract: Per-matrix singular value decomposition (SVD) truncation is Eckart-Young optimal in the whitened Frobenius norm, but errors from independently compre...
SHIFT-LLM is a training‑free post‑pruning correction framework that inserts a Linear Residual Adapter (LRA) at each depth‑pruned site in large language models. Each LRA preserves the original residual identity while adding a lightweight affine correction calibrated via closed‑form least‑squares regression on a small held‑out set, thereby approximating the hidden state that would have been produced by the removed block. Experiments across multiple model families and benchmarks show that SHIFT‑LLM consistently recovers accuracy lost to depth pruning, achieving gains up to +15.7 points on Llama‑3.1‑8B‑Instruct with only a few hundred calibration samples and no gradient computation.
arXiv:2607.12550v3 Announce Type: replace-cross Abstract: The key-value (KV) cache has become the dominant memory cost of transformer inference: it grows with batch size, context length, and depth, a...
arXiv:2608. 08506v1 Announce Type: new Abstract: Training-free low-rank compression frameworks have been gaining prominence for LLM compression given their effectiveness in reducing model parameter count while maintaining task-level accuracy.
arXiv:2607. 12550v1 Announce Type: new Abstract: The key-value (KV) cache has become the dominant memory cost of transformer inference.
arXiv:2606. 29223v1 Announce Type: new Abstract: Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate depths.
Task-Aware Spectral Pruning (TASP) is a post‑training framework that tailors sparse masks to specific tasks by calibrating module‑level spectral descriptors against task‑specific ablation effects. It constructs masks that close grouped‑query‑attention and SwiGLU dependencies, routing each user turn to a single compiled mask that remains fixed during prefill and decoding. In experiments, TASP achieves a 43% active‑FLOP reduction while preserving 97.7% of the dense BF16 performance on Llama‑3‑70B, and delivers a 1.44× speedup on an A100 80GB with INT8‑weight/BF16‑compute, reducing decode latency from 45.2 to 31.3 ms/token.
arXiv:2602. 00161v2 Announce Type: replace-cross Abstract: In this paper, we formulate the compression of large language models (LLMs) by optimally deleting transformer blocks (``block removal'') as a constrained binary optimization (CBO) problem that can be mapped to a physical system (Ising glass), whose energies are a strong proxy for downstream model performance.
arXiv:2606. 26587v1 Announce Type: cross Abstract: Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern accelerators, yet combining them for LLM activation compression remains challenging: activations contain input-dependent outliers that dominate block scales in FP4 quantization, and directly applying N:M sparsity masks discards moderate values, coupling sparsification loss with quantization error.