Model card: vLLM server (frida-decisions 0.2.0)
#1
by artemsnegirev - opened
Adds the vLLM server paragraph (serve command, approximate latency and throughput, razvilka 654/735) and moves the install pins to v0.2.0. Same text as model_card/README.md at github.com/ai-forever/FRIDA-Decisions v0.2.0.
Merged: frida-decisions 0.2.0 adds the vLLM backend.
ai-forever changed pull request status to merged