AI
CoreWeave launches RL Rollouts to speed AI inference and model iteration
CoreWeave introduces a preview capability built on Nvidia’s Dynamo framework to accelerate agentic model training and reduce reload latency.
vLLM
Everything Threat Times has reported about vLLM: 2 stories, newest first. Part of our AI coverage.
Tech News
vLLM Semantic Router Releases Decision 3.0 Multimodal Models
The team released five Apache-2.0 models that return decision probabilities for text and images without generating natural language output.