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.
0.0.104
1. Fix AMD GPU utilization 100%(incomplete), see https://github.com/gpustack/llama-box/issues/23. 2. Support HYGON GPU. 3. Reduce VRAM occupation when no GPU offloaing.
0.0.103
1. Allow distributing deploy Q*K(_M) model; 2. Support DeepSeek v3; 3. (BC) Do NOT compatible with the previous RPC server.
0.0.102
1. Fix Embedding crashing; 2. Support Lora per request; 3. Support multiple-level verbosity logging.