* server : add arg for disabling prompt caching Disabling prompt caching is useful for clients who are restricted to sending only OpenAI-compat requests and want deterministic responses. * address review comments * address review comments |
||
|---|---|---|
| .. | ||
| arg.cpp | ||
| arg.h | ||
| base64.hpp | ||
| build-info.cpp.in | ||
| chat-parser-xml-toolcall.cpp | ||
| chat-parser-xml-toolcall.h | ||
| chat-parser.cpp | ||
| chat-parser.h | ||
| chat-peg-parser.cpp | ||
| chat-peg-parser.h | ||
| chat.cpp | ||
| chat.h | ||
| CMakeLists.txt | ||
| common.cpp | ||
| common.h | ||
| console.cpp | ||
| console.h | ||
| download.cpp | ||
| download.h | ||
| http.h | ||
| json-partial.cpp | ||
| json-partial.h | ||
| json-schema-to-grammar.cpp | ||
| json-schema-to-grammar.h | ||
| llguidance.cpp | ||
| log.cpp | ||
| log.h | ||
| ngram-cache.cpp | ||
| ngram-cache.h | ||
| peg-parser.cpp | ||
| peg-parser.h | ||
| preset.cpp | ||
| preset.h | ||
| regex-partial.cpp | ||
| regex-partial.h | ||
| sampling.cpp | ||
| sampling.h | ||
| speculative.cpp | ||
| speculative.h | ||
| unicode.cpp | ||
| unicode.h | ||