This technical comparison evaluates three open-weight language models released by Chinese AI labs in 2026. Kimi K3, at 2.8 trillion…
Clara Chong describes context engineering as the practice of strategically shaping the information provided to AI agents to optimize performance.…
This guide details how to deploy the open-weight GLM 5.2 model on enterprise infrastructure for cybersecurity incident response, arguing that…
POCKET is a 34.66-billion-parameter sparse Mixture-of-Experts model engineered for efficient on-device inference by activating only about 3 billion parameters per…
PyTorch’s Helion, a domain-specific language for performance-portable ML kernels, now compiles to optimized TPU code via Pallas using a two-level…
This technical report examines automated LLM evaluation systems, arguing the field has shifted from reference-based metrics like BLEU and ROUGE…
The vLLM AFD plugin introduces Attention-FFN Disaggregation, separating a Mixture-of-Experts model’s attention and FFN components into independently deployed services that…
The vLLM team details engineering work to serve Moonshot AI’s Kimi K3 model at production scale, including a prefix-caching design…
NVIDIA released Cosmos 3 Edge on July 20, 2026, a 4-billion-parameter world model built for robots and vision AI agents…
Korean startup VIDRAFT released Aether-7B-5Attn on July 19, 2026, a 6.59-billion-parameter language model published with full training data recipes, code,…
A July 21, 2026 piece examines how AI agent systems can improve autonomously by evolving the harness code around a…
The PyTorch Foundation published a July 22, 2026 update on Q2 progress across its six hosted projects. Highlights include PyTorch…
