DeepSeek V4: the most expected open-source model ever released, and the quietest landing
After 15 months of incremental updates, leaks, and rumored leaks, DeepSeek released version 4. It arrived without the fanfare R1 and R1-preview commanded in ...
Creating highly efficient agents: 450M tool-calling tokens distilled for post-training from top open-source models
Harnesses If you've used Claude Code or Codex, you've used a harness. A harness is the infrastructure layer that wraps an AI coding agent and decides how it ...
How to serve Kimi-K2-Instruct on Lambda with vLLM
When your model doesn’t fit on a single GPU, you suddenly need to target multiple GPUs on a single machine, configure a serving stack that actually uses all ...
Ready to build?
Contact us to learn more about our Managed Kubernetes service and how it can help you accelerate your AI initiatives.