Major changes:
- Support
chat_ubatch_size
andembedding_ubatch_size
- Upgrade to
rag-api-server v0.13.0
: https://github.com/LlamaEdge/rag-api-server/releases/tag/0.13.0 - Upgrade to
llama-api-server v0.16.2
: https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.2 - Upgrade to
ggml plugin b4466
- Upgrade to
server-assistant v0.4.1
Components
CLI Tool v0.4.16
rag-api-server v0.13.0
llama-api-server v0.16.2
WasmEdge v0.14.1 with ggml plugin b4466
qdrant v1.11.4
dashboard v3.1
vector v0.38.0
server-assistant v0.4.1