Related papers: DynSplit-KV: Dynamic Semantic Splitting for KVCach…

Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind…

Reinforcement Learning (RL) has emerged as a crucial paradigm for unlocking the advanced reasoning capabilities of Large Language Models (LLMs), encompassing frameworks like RLHF and RLAIF. Regardless of the specific optimization algorithm…

Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference, hindering their scalability for real-time applications like chatbots. To accelerate inference, we store…

Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks. Unfortunately, the immense amount of computations and memory accesses required for LLM training makes them…

KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the…

To reduce memory consumption during LLM inference, prior works have proposed numerous methods that focus on KV cache pruning based on various criteria. While these techniques often accomplish lossless memory reduction on many datasets, they…

The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most…

Versatile Video Coding (VVC), as the latest standard, significantly improves the coding efficiency over its ancestor standard High Efficiency Video Coding (HEVC), but at the expense of sharply increased complexity. In VVC, the quad-tree…

Large language models (LLMs) have demonstrated remarkable performance, but their long-context reasoning remains constrained by the excessive memory required for the Key-Value (KV) cache. This makes KV cache compression a critical step…

The Key-Value (KV) cache reading latency increases significantly with context lengths, hindering the efficiency of long-context LLM inference. To address this, previous works propose retaining a small fraction of KV cache based on token…

Existing key-value (KV) cache compression methods for large language models (LLMs) often rely on token eviction, which risks losing critical local information in both long prefilling and decoding scenarios. When extrapolating beyond the…

Continual learning remains a challenge across various natural language processing (NLP) tasks, as models updated with new training data often risk catastrophic forgetting of previously acquired knowledge. We introduce a discrete key-value…

Recent advances in large language models (LLMs) have showcased exceptional performance in long-context tasks, while facing significant inference efficiency challenges with limited GPU memory. Existing solutions first proposed the…

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…

Long-context inference in decoder-only language models is costly because long prompts are processed during Prefill, cached at every layer, and repeatedly attended to during autoregressive Decode. We introduce \emph{Shallow Prefill, dEEp…

KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

The computational cost of training a vision-language model (VLM) can be reduced by sampling the training data. Previous work on efficient VLM pre-training has pointed to the importance of semantic data balance, adjusting the distribution of…

Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV caching. We introduce CDLM (Consistency Diffusion Language…