65a 4afb0a746f server : Support multimodal completion and embeddings prompts in JSON format (#15108) ...

- Use server_tokens in more places in server and util.cpp
- Convert most functions that used llama_tokens to server_tokens
- Modify input tokenizer to handle JSON objects as subprompts
- Break out MTMD prompt parsing into utility function
- Support JSON objects with multimodal_data arrays for MTMD prompts along with other existing types
- Add capability to model endpoint to indicate if client can send multimodal data
- Add tests.

2025-08-22 10:10:14 +02:00

53 KiB

Raw Blame History

View Raw