v0.0.107

1. Fix crash on truncating long kv cache;
2. Fix crash on chatting with the image which has Alpha channel;
3. Fix VRAM occupations when zero offloading with --mmproj;
4. Compatible with some GGUF files which described the wrong kv_count, e.g: CompendiumLabs/bge-large-zh-v1.5-gguf/FP16.

v0.0.106

1. Remove the VRAM occupation when zero offloading: -ngl 0;
2. Fix rerank model loading error: gpustack/gte-multilingual-reranker-base-GGUF, gpustack/jina-reranker-v2-base-multilingual-GGUF
3. Support tool calling in ChatGLM4 series;
4. Introduce DDIM(ddim_trailing) sample method;
5. Support multiple devices offloading image model.

v0.0.105

1. Fix RPC Server calling;
2. Fix SD3.x image generation problem;
3. Support assistant role chat with image message type;
4. Support using data URL(http://, https://) in image message type.

v0.0.104

1. Fix AMD GPU utilization 100%(incomplete), see #23.
2. Support HYGON GPU.
3. Reduce VRAM occupation when no GPU offloaing.

v0.0.103

1. Allow distributing deploy Q*K(_M) model;
2. Support DeepSeek v3;
3. (BC) Do NOT compatible with the previous RPC server.

v0.0.102

1. Fix Embedding crashing;
2. Support Lora per request;
3. Support multiple-level verbosity logging.

v0.0.101

refactor: log verbosity

Signed-off-by: thxCode <[email protected]>

v0.0.100

docs: readme

Signed-off-by: thxCode <[email protected]>

v0.0.99

refactor: meta

Signed-off-by: thxCode <[email protected]>

v0.0.98

ci: fix build

- windows amd64
- remove darwin ccache

Signed-off-by: thxCode <[email protected]>