guarded-hotshard
Tenant-aware request scheduling for LLM inference. Cuts premium-tenant p99 latency 60-70% on a contested GPU at <5% extra cost.
Installation
In a virtualenv (see these instructions if you need to create one):
pip3 install guarded-hotshard
Dependencies
Releases
| Version | Released | Bullseye Python 3.9 |
Bookworm Python 3.11 |
Trixie Python 3.13 |
Files |
|---|---|---|---|---|---|
| 0.2.0 | 2026-05-02 | ||||
| 0.1.0 | 2026-05-02 | ||||
Issues with this package?
- Search issues for this package
- Package or version missing? Open a new issue
- Something else? Open a new issue