Llama-cpp-python

- feat: Update llama.cpp to ggerganov/llama.cpp2aed77eb06a329f0d82bb1c467f4244904d4073f
- feat: Add mistral instruct chat format as "mistral-instruct" by Rafaelblsilva in 799

- feat: Update llama.cpp to ggerganov/llama.cppd2f650cb5b04ee2726663e79b47da5efe196ce00

- feat: Update llama.cpp to ggerganov/llama.cpp6db2b41a76ee78d5efdd5c3cddd5d7ad3f646855
- feat: Add json schema mode by abetlen in 1122

- feat: Update llama.cpp to ggerganov/llama.cppfaa3526a1eba458120987ed8269e5616385a76f4
- feat(server): include llama-cpp-python version in openapi spec by abetlen in cde7514c3d28e6d52f272614e9957208c344dde5
- fix: use both eos and bos tokens as stop sequences for hf-tokenizer-config chat format. by abetlen in 5b982d0f8c6f35242c8862ffdce00e17cea0b44f
- fix: GGUF metadata KV overrides, re 1011 by phiharri in 1116
- fix: llama_log_set should be able to accept null pointer by abetlen in c970d41a85381fd55235136f123422df0bf0c7e7

- feat: Update llama.cpp to ggerganov/llama.cpp504dc37be8446fb09b1ede70300250ad41be32a2
- fix: from_json_schema oneof/anyof bug by jndiogo in d3f5528ca8bcb9d69d4f27e21631e911f1fb9bfe
- fix: pass chat handler not chat formatter for huggingface autotokenizer and tokenizer_config formats by abetlen in 24f39454e91cf5dddbc4b6041aead4accc7c7a2d
- feat: Add add_generation_prompt option for jinja2chatformatter by abetlen in 7f3209b1eb4ad3260ba063801fab80a8c25a2f4c
- feat: Add Jinja2ChatFormatter by abetlen in be09318c26add8674ce494ae7cc480cce72a4146
- feat: Expose gguf model metadata in metadata property by abetlen in 5a34c57e5479e50c99aba9b38218cc48e6560b81

- feat: Update llama.cpp to ggerganov/llama.cppa5cacb22b2114fd9adf61c00cbb237384d86bced
- fix: Mirostat sampling now passes correct type to ctypes and tracks state during generation by abetlen in 3babe3512cb95743108f2b595210c38ed6f1b904
- fix: Python3.8 support in server by abetlen in 141293a75b564a8699e0acba1da24d9aa1cf0ab1