A year of LLM serving workloads in production
A paper examining a year of production LLM traffic reports workload changes, short-lived prefix reuse, and tradeoffs between KV-cache locality and load balancing.
Read articleKnowledge you can apply
Daily bookmarks: relevant news, facts and discoveries.
A paper examining a year of production LLM traffic reports workload changes, short-lived prefix reuse, and tradeoffs between KV-cache locality and load balancing.
Read articlePublished on August 20, 2026, the free book recounts an attempt to pretrain a 1.02-billion-parameter MoE model on an H200.
Read articleIn an announcement dated August 20, 2026, dstack presents Presets, an open-source toolkit that uses agents to simplify inference optimization and provides a portable format for its results.
Read articleAn article covers CuTe layout representation and algebra, a relevant topic for engineers working with layout abstractions in GPU programming.
Read articleMovfuscator turns C into Turing-complete assembly using only the MOV instruction, showing how restricting a compiler’s output can complicate code analysis.
Read articleA post dated August 17, 2026 reports that different prompts in two DSH tools triggered a 3.5-second timeout; after a constant was changed, one command reportedly fell from 3,600 ms to 158 ms.
Read articleAuthors of a USENIX Security paper report overlap between leaked Geedge Networks source code and China’s Great Firewall, including DNS and RST injection behavior.
Read articleA post dated August 16, 2026 describes weighted top-k SQL sampling for a reinforcement-learning replay buffer and reports selecting 8,192 rows from 50 million in about 1.1 seconds on a laptop.
Read articleVersion 0.10.0 introduces an executor for pipelines on a jobs service, support for storage buckets as data folders, and preservation of reasoning outputs in inference results.
Read articleAn article published on August 13, 2026, follows an LDG.E SASS instruction through the RTX 4090’s hardware units and memory hierarchy, including reverse engineering of undocumented details.
Read articleA technical article published on August 13, 2026, discusses using swizzling to address bank conflicts in CUDA shared memory, a memory-access issue that can affect CUDA kernel performance.
Read articleAn article dated August 12, 2026 presents an AI framework for simulating coordinated, adaptive influence campaigns.
Read articlePublished on August 12, 2026, the bookmark recommends LeetGPU challenges for CUDA practice and outlines a progression from naive SIMD kernels to more advanced techniques and tools.
Read articlePublished on August 11, 2026, the text describes hooks that send prompts for security checks before inference, allowing an organization to permit or deny each request.
Read articleResearch published on August 10, 2026 describes an evaluation of AI agents’ ability to turn vulnerabilities into concrete impacts, such as unauthorized file access or code execution.
Read articleResearch explores reinforcement learning in simulated clinical consultations, involving patient history, diagnostic hypotheses, and decisions under uncertainty.
Read articlePublished on August 9, 2026, this community benchmark compares seven self-hosted memory providers for Hermes Agent, using 71,060 conversation turns and 3,750 questions about facts that change over time.
Read articlePublished on August 9, 2026, the entry describes EnvACE, a reinforcement-learning method that alternates tool-call generation and internal world rehearsals during training.
Read articlePublished on August 9, 2026, obfus.h is described as a macro header for compile-time C obfuscation on Windows x86/x64 using tcc.
Read articleA post published on August 9, 2026 describes kits that relay login and MFA interactions with a real service to intercept the resulting session cookie. It cites Evilginx, Modlishka, and Muraena.
Read articleRota Nacional
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.