Home
Projects
Resources
Alternatives
Blog
Sign In
Orkhon Versions
Save
Orkhon: ML Inference Framework and Server Runtime
Overview
Versions
Reviews
Resources
v0.2.0
3 years ago
This release comes with:
ONNX interface
New asynchronous servicing methods
Shareable server runtime
Nuclei asynchronous runtime
Inferring input facts for frozen model
Improves throughput:
~4.8361 GiB/s prediction throughput
3_000 concurrent requests take ~4ms on average
Home
Projects
Resources
Alternatives
Blog
Sign In
Sign In to OSA
I agree with
Terms of Service
and
Privacy Policy
Sign In with Github