Stories by rrampage
Test-Time Scaling (TTS) is an important method for improving the performance of Large Language Models (LLMs) by using additional computation during the inference phase. However, current studies do not systematically analyze how policy models, Process Reward Models (PRMs), and problem difficulty infl...
Learning CUDA by optimizing matrix-vector multiplication for cuBLAS-like perf
(maharshi.bearblog.dev)
Paper: https://arxiv.org/abs/2509.12539
When SSRF Is Enough: Full Docker Escape on Windows Docker Desktop(CVE-2025-9074)
(blog.qwertysecurity.com)