arXiv:2608. 05326v1 Announce Type: new Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache.
arXiv:2606. 02011v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive.
Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive. While low-bit quantization reduces per-token decoding cost, we show that aggressive 2-bit inference can fail to deliver end-to-end speedup because instability in the generation process inflates total token count.
The paper introduces OnQ, a low‑bit recovery pipeline for quantized large language models that uses on‑policy distillation and candidate‑wise Dynamic KL to address trajectory divergence and distributional misalignment. OnQ starts with block‑wise calibration, then lets the quantized student generate responses and receive full‑precision teacher supervision on its own prefixes, dynamically weighting forward and reverse KL losses per candidate. Experiments on Qwen3 models show that OnQ outperforms baselines on nine benchmarks, especially long‑horizon reasoning, and produces shorter, less truncated responses.
BeaconKV is a training‑free key‑value cache compression technique for Large Reasoning Models that uses beacon queries—compact representatives of query clusters—to predict which KV pairs will be revisited during long‑horizon reasoning. By focusing on Thought Revisiting Tokens that re‑attend distant context, BeaconKV reduces memory usage up to 5.8× and improves throughput by over 4.3× while largely preserving cache accuracy across multiple open‑source LRMs and reasoning benchmarks.
arXiv:2606. 26488v1 Announce Type: new Abstract: Recursive reasoning models can solve complex structured tasks with only a few million parameters by repeatedly updating a latent state.
OBC‑Prune introduces an outcome‑based calibration approach for pruning large reasoning models, focusing on the causal importance of each reasoning sentence rather than uniform activation salience. By pairing correct and incorrect rollouts and using intervention‑based analysis, it assigns per‑token weights that guide one‑shot pruning methods such as SparseGPT, Wanda, and ALPS. Experiments on DeepSeek‑R1‑Distill‑Qwen models show consistent accuracy gains and shorter reasoning traces across multiple benchmarks at 40‑50% sparsity.
arXiv:2606. 25519v1 Announce Type: cross Abstract: Quantization is widely used to reduce the inference cost of large language models, but its effect on reasoning models is not fully captured by final-answer accuracy or per-token latency.
arXiv:2606. 15682v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong problem-solving through long chain-of-thought, but their deployment is constrained by the high cost of full-precision inference and growing KV cache footprints.
arXiv:2609.36760v1 Announce Type: new Abstract: Multi-Head Latent Attention (MLA) enables expressive multi-head attention with compact caches for its content and decoupled RoPE paths, yet cache memor...
arXiv:2606. 03928v1 Announce Type: new Abstract: Reasoning models improve accuracy through extended chains of thought, but their long outputs create a memory and compute bottleneck.
arXiv:2509.14093v3 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting can substantially improve the reasoning ability of large language models (LLMs), but it often comes with hig...