arXiv:2606. 20005v1 Announce Type: cross Abstract: Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, model compression, continual learning, and sparse-attention LLM training.
arXiv:2606. 09079v1 Announce Type: cross Abstract: Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving.
arXiv:2605. 01910v2 Announce Type: replace-cross Abstract: Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all $n_k$ key and value vectors from KV cache.
arXiv:2608. 03796v1 Announce Type: cross Abstract: Small language models are often the only option for deployment under tight latency, cost, and on-premises constraints, but they are rarely trained from scratch: a compressed model is usually recovered through knowledge distillation (KD).
arXiv:2604. 00004v2 Announce Type: replace-cross Abstract: The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by lightweight Continual Pre-Training (CPT).
arXiv:2606. 02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation.
arXiv:2605. 15422v3 Announce Type: replace Abstract: Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared prompt of P tokens, but standard FlashAttention replicates all P prompt tokens N times across both forward and backward passes -- duplicating compute and memory on identical hidden states.
arXiv:2606. 13392v1 Announce Type: new Abstract: Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale.
arXiv:2608. 15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads.
arXiv:2507. 07247v2 Announce Type: replace-cross Abstract: As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central computational bottleneck due to their high memory and time complexity.
arXiv:2606. 04511v1 Announce Type: cross Abstract: Sparse attention reduces compute and memory bandwidth for long-context LLM inference.
arXiv:2603. 17484v2 Announce Type: replace-cross Abstract: Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval.
arXiv:2606. 19348v1 Announce Type: cross Abstract: We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.