issues
search
ray-project
/
llmperf
LLMPerf is a library for validating and benchmarking LLMs
Apache License 2.0
659
stars
113
forks
source link
feat: Client Added for Predibase
#40
Open
bhaba-ranjan
opened
8 months ago
bhaba-ranjan
commented
8 months ago
Hello,
This pull request adds Ray Client for
Predibase
.
Predibase is an open-source LLM inference server. It can serve multiple LoRA adapters, in a single deployment.
The pull request targets
/generate_stream
endpoint which streams token.
API spec can be found here:
Predibase Swagger
Hello,
/generate_stream
endpoint which streams token.