pyptx brings a Python DSL to NVIDIA PTX kernels
Published on April 25, 2026, pyptx is described as a Python DSL for writing NVIDIA PTX kernels, with Hopper and Blackwell support and integration with JAX and PyTorch.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
StructMem proposes temporal memory for LLM agents
Published on April 24, 2026, the StructMem paper proposes hierarchical memory for long-term conversational agents, targeting event relations, temporal reasoning, and multi-hop questions.
Read articleDFlash and DDTree run Qwen3.6-27B on an RTX 3090
A post published April 23, 2026 reports 73 tokens per second for Qwen3.6-27B on a single RTX 3090, using speculative decoding with DFlash and DDTree. The author says the stack loads the model because its architecture and layer and head dimensions match Qwen3.5, but throughput is lower.
Read articleGPU kernels for LLM operations
On April 23, 2026, a company announced GPU kernels for language-model operations, developed with TileLang. The company says some are already used internally for training and inference.
Read articleMegatron-LM: model parallelism for large-model training
A 2019 paper describes splitting the weights of language models with billions of parameters across GPUs, addressing models whose weights do not fit on a single GPU.
Read articleFil-C aims to add memory safety to C/C++ builds
A report published on April 22, 2026 describes Fil-C as a compiler for C/C++ projects with memory safety and notes that direct assembly calls may need alternatives.
Read articleLRT explores reasoning with compact representations
Published on April 22, 2026, the post introduces Latent Reasoning Tuning (LRT), an approach that trains models to reason with compact internal representations rather than long text sequences.
Read articleWhat limits knowledge in attention and MLPs
A study examines how attention matrices and MLPs store knowledge, highlighting limits tied to data, finite compute, and noise in long contexts.
Read articleTACO explores context compression for terminal agents
A framework discovers and refines rules for compressing context from terminal-agent interactions. The paper reports tests on three benchmarks.
Read articleLoop transformers and energy-based inference
Published on April 22, 2026, the text links residual updates in looped transformers to gradient descent on an energy function, subject to a specific condition on the block.
Read articleHybridGen coordinates CPU and GPU for long contexts
The proposed framework enables collaborative attention between CPU and GPU, using CXL memory to support long-context language-model inference.
Read articleRadar: weekly roundup features research on AI agents
Published on April 21, 2026, the roundup highlights work on agentic system design for Claude Code, long-term tasks, memory transfer in coding agents, distillation, and other topics.
Read articleCliffordNet explores Clifford algebra in neural networks
The architecture combines inner-product and geometric interactions without attention or mixer layers; the report gives 77.82% accuracy on CIFAR-100 with 1.4 million parameters.
Read articleLACE coordinates parallel reasoning paths
Published on April 20, 2026, the brief describes LACE, a framework that lets parallel paths share intermediate ideas and correct one another through cross-thread attention.
Read articleGNU C Library Reference Manual
Published on April 20, 2026, this item points to a PDF copy of the GNU C Library Reference Manual, intended for engineers working with the library.
Read articleSkill-RAG adapts retrieval to knowledge gaps
Published on April 20, 2026, the paper presents a method that detects possible knowledge gaps and routes queries to specialized retrieval strategies. Its evaluation covers three question-answering datasets.
Read articleProtocol proposes auditable self-improvement for agents
Published on April 19, 2026, this item summarizes a paper proposing audit and rollback mechanisms for agents that suggest, evaluate, and implement improvements.
Read articleAutoSOTA automates iterative AI research
Published on April 19, 2026, the report describes AutoSOTA, a system with eight specialized agents that reproduces and improves models from AI papers.
Read articleGuide compares attention mechanisms in LLMs
An article published on April 19, 2026, presents more than 13 attention mechanisms and their role in how Transformers and LLMs process context and memory.
Read articleCompute and memory costs in loop models
Published on April 19, 2026, the article analyzes seven loop model variants and how gradient structure affects FLOPs and memory during training.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.