llama.cpp

c42712b0 - server: support multiple generations from one prompt (OAI "n" option) (#17775)

server: support multiple generations from one prompt (OAI "n" option) (#17775) * backend support * server: support multiple generations from one prompt (OAI "n" option) * fix invalid batch * format oai * clean up * disable ctx shift * add test * update comments * fix style * add n_cmpl to docs [no ci] * allowing using both n_cmpl and n