Evaluating LLMs across many model variants—quantized, fine-tuned, or deployment-specific—requires running large benchmarks repeatedly, a process that can take tens of hours per model on edge hardware such as NPUs. Existing subset selection methods reduce this cost but depend on large calibration pools or learned prediction layers. We introduce MINCE (Monte Carlo Informed N-sizing for Compact Evaluation), which uses Monte Carlo simulation over per-item logs from a small set of calibration models to find the minimum subset size that bounds accuracy drift and then fixes a randomly sampled subset at that size, with no prediction layer needed. MINCE reduces IFEVAL by 54%, MMLU by 89%, GSM8K by 70%, and MMLU-Pro by 88% with maximum drift ≤2.62 pp on BF16 calibration models. The frozen subsets generalize to held-out GPU models with mean drift ≤1.40 pp and to INT4 NPU models with mean drift of 0.77–3.59 pp, while delivering evaluation speedups of up to 8.1× on the GPU models and evaluation speedups of 1.7–3.4× on the NPU models. The method is robust to calibration pool size and achieves lower drift than tinyBenchmarks (12× lower on MMLU, 3.3× on GSM8K) while using 42× fewer calibration models.

Context-heavy agents place substantial pressure on the key–value (KV) cache: long prefixes are reused across many short turns, while concurrency determines whether the serving system can keep GPUs utilized. We study 4-bit KV-cache compression for this setting, using TurboQuant-style rotation and codebook quantization as a quality anchor and vLLM FP8 KV caching as the deployment anchor. We report three contributions. First, we frame 4-bit KV caching around multi-round agent workloads where task quality, cache residency, and serving throughput must be measured jointly. Second, we describe the practical design choices needed to make the 4-bit path robust, including asymmetric K/V treatment, Walsh–Hadamard rotation, QJL removal, and block-scale variants. Third, we present serving optimizations on AMD GPUs, including optimized decode-attention kernels and UltraQuant, an FP4 approximation path that uses FP8 queries, FP4 KV tensors, UE8M0 group scales, and native scaled-MFMA support on CDNA4. On an adaptive-SLO replay of production Claude Code traces, UltraQuant sustains 2.71× (MiniMax-M2.5) and 4.38× (Qwen3-235B) the qualified-request throughput of the BF16 baseline, matching or exceeding hardware FP8 KV while using half the KV bytes. UltraQuant delivers its largest gains in long-context, high-concurrency, memory-constrained serving regimes.

Long-context Large Language Models (LLMs) face significant memory bottlenecks during inference due to the linear growth of key-value (KV) cache with sequence length. While individual optimization techniques like KV cache quantization, chunked prefill, and model weight quantization have shown promise, their joint effects and optimal configurations for edge deployment remain underexplored. We introduce KV Pareto, a systems-level framework that systematically maps the trade-off frontier between total memory consumption and task accuracy across these three complementary optimization techniques. Our framework evaluates multiple LLM architectures (Qwen, Llama, Mistral) with varying KV quantization schemes (int2/4/8, mixed-precision), granularities (per-token, per-tensor, per-block), and 4-bit weight quantization via AWQ. Our framework identifies model-specific Pareto-optimal configurations that achieve 68-78% total memory reduction with minimal (1-3%) accuracy degradation on long-context tasks. We additionally verify the selected frontiers on additional benchmarks of Needle-in-a-Haystack, GSM8k and MMLU as well as extended context lengths of up to 128k to demonstrate the practical need of joint optimization for efficient LLM inference.

Inference optimizations such as quantization, pruning, format and datatype conversion, model export, and serialization can lead to functional degradations in language model task performance. While most efforts on performance recovery for deployment focus on robust quantization techniques, we focus on recovering model accuracies from any sources that degrade model weights, such as improper model serialization. In this work, we propose Recover-LoRA, a lightweight and dataset agnostic method to recover accuracy in degraded models. Recover-LoRA uses synthetic data and logit distillation to learn LoRA adapters on selective layers that facilitate aligning the degraded model to its full precision model. We investigate the utility of Recover-LoRA across a diverse set of small language models (SLMs), including models with varying attention architectures, multi-head attention (MHA) and group-query attention (GQA), as well as several evaluation datasets. Our results show that Recover-LoRA recovers model accuracies by 5-17% on MHA and GQA SLMs.

Pre-trained language models (PLMs) are engineered to be robust in contextual understanding and exhibit outstanding performance in various natural language processing tasks. However, their considerable size incurs significant computational and storage costs. Modern pruning strategies employ retraining-free one-shot techniques to compress PLMs; however, these approaches often lead to an indispensable reduction in performance. In this paper, we propose SDS, a Sparse-Dense-Sparse pruning framework to enhance the performance of the pruned PLMs from a weight distribution optimization perspective. We outline the pruning process in three steps. Initially, we prune less critical connections in the model using conventional one-shot pruning methods. Next, we reconstruct a dense model featuring a pruning-friendly weight distribution by reactivating pruned connections with sparse regularization. Finally, we perform a second pruning round, yielding a superior pruned model compared to the initial pruning. Experiments demonstrate that SDS outperforms the state-of-the-art pruning techniques SparseGPT and Wanda under an identical sparsity configuration. For instance, SDS reduces perplexity by 5.16 on Raw-Wikitext2 and improves average accuracy by 3.86% across multiple zero-shot benchmarks for LLaMA-3-8B compared to Wanda with 2:4 sparsity.