When will it be merged into llama.cpp master?

[joey-zmw]

When will it be merged into master?
After compiling using the branch, starting the service results in the following error:
git fetch origin pull/26185/head:pr‑26185‑kimi3‑text
....
./llama-server -m /data3/Kimi-K3-UD-Q2_K_XL-00001-of-00019.gguf --mmproj /data3/Kimi-K3-mmproj-F32.gguf -c 0 -t 96 --port 8033 --host 0.0.0.0
0.00.002.796 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the -lv N CLI arg)
0.00.003.241 W srv llama_server: -----------------
0.00.003.244 W srv llama_server: CORS is set to allow all origins ('*') and no API key is set
0.00.003.244 W srv llama_server: this can be a security risk (cross-origin attacks)
0.00.003.244 W srv llama_server: more info: ggml-org/llama.cpp#25655
0.00.003.245 W srv llama_server: -----------------
0.00.004.529 I srv load_model: loading model '/data3/Kimi-K3-UD-Q2_K_XL-00001-of-00019.gguf'
0.00.005.357 E mtmd_get_memory_usage: error: Failed to load CLIP model from /data3/Kimi-K3-mmproj-F32.gguf

0.00.005.360 E srv load_model: [mtmd] failed to get memory usage of mmproj
0.01.711.602 W load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect