Skip to content
This repository was archived by the owner on Jan 7, 2026. It is now read-only.

Releases: notsyncing/azarrot

0.3.0

08 Sep 08:31
@notsyncing notsyncing
0.3.0
1657dd7

Choose a tag to compare

View all tags
0.3.0 Latest
Latest
  • Add docker image build
  • Support list input of text on embeddings API
  • Support downloading model from huggingface
  • Support auto-batching on chat API
  • Support top_p, temperature and seed parameters in chat API
  • Update OpenVINO to 2024.3.0
  • Update IPEX-LLM to 2.1.0
Assets 2
Loading

0.2.0

04 Aug 08:34
@notsyncing notsyncing
0.2.0
252a3ae

Choose a tag to compare

View all tags
0.2.0
  • Add IPEX-LLM backend
  • Support InternVL2 on IPEX-LLM backend with OpenAI chat completion image input
  • Support Qwen2 tool calling on IPEX-LLM and OpenVINO backend with OpenAI chat completion tools input
  • Support embedding models on IPEX-LLM and OpenVINO backend with OpenAI embedding API
  • Support parallel completion requests: concurrent completion requests can be submit on both OpenVINO and IPEX-LLM backends (not batching)
  • Add README and changelog
Loading