Talk explores memory-centric computing
A PDF of Onur Mutlu’s talk at EFCL Winter School 2026 presents an approach aimed at performance challenges related to memory.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
Darkweb Scanner monitors keywords on .onion sites
Published on February 26, 2026, this entry presents an OSINT tool for monitoring keywords on .onion sites, with a stated focus on threat intelligence and brand monitoring.
Read articleOpenAnonymity proposes unlinkable AI inference
Published on February 26, 2026, the post presents an approach intended to prevent AI providers from linking inference calls to individual users. It says the approach was integrated into open-source infrastructure and a chat app.
Read articleA CUDA matrix optimization diary
Published on February 26, 2026, the diary describes iterative optimization of a CUDA matrix multiplication kernel and decisions made while seeking performance close to cuBLAS.
Read articlePadding for reusing CUDA graphs
Published on February 26, 2026, the summary describes a strategy for inference workloads with variable sequence lengths: set a maximum input size, pad inputs to the nearest bucket, and create a family of CUDA graphs. According to the author, this avoids recompilations.
Read articlePraetorian's multi-agent pipeline for CVE detection templates
Praetorian describes a multi-agent pipeline that turns CVE research into validated Nuclei detection templates, using specialized agents, three model providers and an actor-critic refinement loop.
Read articleCUDA matrix transposition with shared memory
Published on February 26, 2026, Mark Harris’s article discusses how shared memory can improve matrix transposition performance in CUDA C/C++.
Read articleTutorial covers techniques for dLLMs
Published on February 25, 2026, this roughly 22-minute tutorial discusses inference and training for diffusion language models (dLLMs).
Read articleGuide explores creating a virtual iPhone
A guide published in a GitHub repository may be a reference for engineers interested in exploring virtual iPhone configurations. The available description does not detail steps or technical requirements.
Read articleCUDA kernel patterns: four core operations
Published on February 25, 2026, the record highlights reduction, 1D convolution, histogram, and numerically stable softmax as key CUDA kernel patterns, with techniques for parallelization and memory use.
Read articleRL recipes for math, code, and tool use
Prime Intellect’s documentation collects practical reinforcement-learning training recipes for mathematical reasoning, code generation, tool use, and other tasks in the Lab.
Read articleTechnical analysis of Intel Management Engine
The article examines Intel Management Engine architecture and firmware, exploitation of CVE-2017-5689, a TOCTOU race condition in CVE-2025-20037, PKfail, and detection methods.
Read articleQLoRA demonstration uses 50 model outputs
Published on February 24, 2026, the post describes a local distillation demonstration: 50 GPT-5.2 outputs were used to fine-tune Llama 3B with QLoRA. The author says the process transferred significant capabilities.
Read articleSecure Erasure in Magnetic and Solid-State Storage
Peter Gutmann’s 1996 article discusses data remanence and the limits of a single overwrite on magnetic media.
Read articleHPC++ aims to parallelize C++ for CPUs and GPUs
A February 22, 2026 entry describes an LLVM-based framework that turns sequential C++ programs into parallel implementations for multicore CPUs and OpenCL-compatible GPUs.
Read articlentransformer claims Llama 70B runs on an RTX 3090
Published on February 22, 2026, the entry describes a C++/CUDA inference engine that claims to run Llama 70B on an RTX 3090, transferring data from NVMe to the GPU without passing through the CPU.
Read articlellmfit estimates model compatibility with local hardware
A February 21, 2026 entry describes llmfit, a tool that analyzes hardware to identify compatible models and estimate performance before downloading weights.
Read articleVulnLLM-R-7B for vulnerability detection
A February 21, 2026 entry presents VulnLLM-R-7B as a reasoning model specialized in vulnerability detection, without reporting benchmarks or quantitative results.
Read articleBooth compiles CUDA for AMD GPUs
Published on February 18, 2026, the bookmark presents Booth as an open-source compiler for CUDA, Triton, and HIP, targeting multiple GPU and CPU architectures.
Read articleBooth explores compilation for GPUs and CPUs
Published on February 18, 2026, the entry describes Booth as an open-source compiler for CUDA, Triton, and HIP, with support for multiple GPU and CPU architectures.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.