- Release MT-bench code and data
- Release new models
- Support more models (Falcon, Salesforce/xgen, Salesforce/codet5p-6b, Robin-7B/13B/33B, Baichuan-7B)
- Integrate vLLM worker for continuous batching and high-throughput serving. See doc.
Don't miss a new FastChat release
NewReleases is sending notifications on new releases.