arXiv:2607. 04244v1 Announce Type: new Abstract: This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.
arXiv:2608. 04048v1 Announce Type: cross Abstract: Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput.
arXiv:2608. 13966v1 Announce Type: new Abstract: As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality.
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
arXiv:2607. 01831v1 Announce Type: cross Abstract: Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems.
arXiv:2606. 04238v1 Announce Type: cross Abstract: Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typically incurs severe accuracy degradation.
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.
arXiv:2601. 22813v2 Announce Type: replace Abstract: The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models such as LLMs.
arXiv:2605. 08692v2 Announce Type: replace Abstract: Post-training weight-only quantization to 4 bits is widely used to reduce the memory and compute costs of large language model inference.
arXiv:2606. 00144v1 Announce Type: cross Abstract: Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple tokens that a verifier validates in parallel.
In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes.
arXiv:2606. 00079v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory.
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.