release v1.0.1

This commit is contained in:
will.yang
2024-05-08 22:23:11 +08:00
parent b81deb2077
commit d59d017d4c
27 changed files with 1140 additions and 76 deletions

17
CHANGELOG.md Executable file
View File

@@ -0,0 +1,17 @@
# CHANGELOG
## v1.0.1
- Optimize model conversion memory occupation
- Optimize inference memory occupation
- Increase prefill speed
- Reduce initialization time
- Improve quantization accuracy
- Add support for Gemma, ChatGLM3, MiniCPM, InternLM2, and Phi-3
- Add Server invocation
- Add inference interruption interface
- Add logprob and token_id to the return value
## v1.0.0
- Supports the conversion and deployment of LLM models on RK3588/RK3576 platforms
- Compatible with Hugging Face model architectures
- Currently supports the models Llama, Qwen, Qwen2, and Phi-2
- Supports quantization with w8a8 and w4a16 precision