koboldcpp/tools/server/tests/unit
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
..
test_basic.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_chat_completion.py server: fix OpenAI API compatibility for usage statistics in chat streams (#15444) 2025-08-21 00:10:08 +02:00
test_completion.py server : Support multimodal completion and embeddings prompts in JSON format (#15108) 2025-08-22 10:10:14 +02:00
test_ctx_shift.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_embedding.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_infill.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_lora.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_rerank.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_security.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_slot_save.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_speculative.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_template.py server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771) 2025-05-26 00:30:51 +01:00
test_tokenize.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_tool_call.py server : disable context shift by default (#15416) 2025-08-19 16:46:37 +03:00
test_vision_api.py server : Support multimodal completion and embeddings prompts in JSON format (#15108) 2025-08-22 10:10:14 +02:00