Skip to content
#

h200

Here are 5 public repositories matching this topic...

Language: All
Filter by language

Thermal-aware batch controller for vLLM/TensorRT-LLM. Prevents HBM thermal throttling from killing p99 latency on H100/H200. Monitors nvidia-smi, auto-cuts batch size at 85°C, migrates cold KV to DRAM. Prometheus + Grafana included. 4.2s -> 2.1s p99 at 128K context.

  • Updated Apr 13, 2026
  • Python

Improve this page

Add a description, image, and links to the h200 topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the h200 topic, visit your repo's landing page and select "manage topics."

Learn more