Latest in Python

252 words

Serving Moonshot AI's Kimi K3.1 Pro with llm-d across TPUs and GPUs

These recipes run here on Google Cloud (GKE), but llm-d's routing, scheduling, and disaggregation layer is accelerator- and cloud-independent. The same configuration pattern applies on other accelerators and clouds; only the device-allocation and KV-transfer connectors change. To sustain high concurrency…

Python

Data, web, automation, packaging, async, and performance for Python stacks.

  • 11 Tracked terms
  • Last 30 days Feed window

What this topic collects on

An article joins this feed when it matches these terms. Each one is also a search of its own.