arXiv:2608. 09160v1 Announce Type: new Abstract: Query-Key Normalization (QK-Norm) improves the training stability and quality of modern Large Language Models (LLMs).
arXiv:2512. 22219v2 Announce Type: replace-cross Abstract: We introduce Mirage Persistent Kernel (MPK), the first compiler and runtime system that automatically transforms multi-GPU model inference into a single high-performance mega-kernel.
arXiv:2606. 16310v1 Announce Type: new Abstract: Query-key (QK) normalization stabilizes attention by controlling the scale of queries and keys before the dot product, but is not immediately compatible with Multi-head Latent Attention (MLA).
arXiv:2607. 16241v1 Announce Type: cross Abstract: Recent large language models (LLMs) can generate custom CUDA kernels that appear to outperform PyTorch on benchmarks such as KernelBench.
arXiv:2607. 22648v1 Announce Type: new Abstract: Inspired by the design of client caching in Content Delivery Networks (CDNs), PTStore distributes and replicates popular tensors that form reusable KV cache prefixes, which are the main technique used by state of art approaches to accelerate inferences.
arXiv:2606. 17781v1 Announce Type: cross Abstract: The rapid growth of Large Language Models (LLMs) has intensified the need for specialized hardware accelerators that can satisfy stringent inference latency and power constraints.
arXiv:2606. 08476v1 Announce Type: cross Abstract: Context parallelism (CP) is essential for training large-scale, long-context language models, as it partitions sequences to reduce memory overhead.
arXiv:2601. 07048v5 Announce Type: replace-cross Abstract: Approximate nearest neighbor search (ANNS) is a core problem in machine learning and information retrieval applications.
arXiv:2505. 18231v3 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large size of key-value (KV) cache.
arXiv:2607. 11976v1 Announce Type: new Abstract: Indexer-TopK, the operation to compute the scores and select the top-k candidates, is widely used by sparse attention kernels in large language models and vector retrieval in recommendation systems and vector databases.
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:2607. 23264v1 Announce Type: cross Abstract: Fine-grained, device-initiated communication lets persistent GPU kernels in distributed diffusion transformer (DiT) inference issue remote stores and overlap data movement with Tensor Core computation.
arXiv:2606. 10493v1 Announce Type: cross Abstract: Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads.