llama.cpp/llama_cpp
Tanner Hobson ef22e478db
Replace logits_to_logprobs implementation with numpy equivalent to llama.cpp (#991)
See #990. This change makes the logits_to_logprobs function equivalent to the version in the llama.cpp repository. It uses numpy so it's much faster than the previous version.
2023-12-11 20:46:27 -05:00
..
server docs: Update openapi endpoint names 2023-11-24 03:39:29 -05:00
__init__.py Bump version 2023-12-11 10:26:42 -05:00
_utils.py Fix UnsupportedOperation: fileno in suppress_stdout_stderr (#961) 2023-12-11 20:44:51 -05:00
llama.py Replace logits_to_logprobs implementation with numpy equivalent to llama.cpp (#991) 2023-12-11 20:46:27 -05:00
llama_chat_format.py Add Pygmalion chat format (#986) 2023-12-11 20:44:04 -05:00
llama_cpp.py Update llama.cpp 2023-12-11 10:21:35 -05:00
llama_grammar.py Add from_json_schema to LlamaGrammar 2023-11-23 00:27:00 -05:00
llama_types.py Add missing tool_calls finish_reason 2023-11-10 02:51:06 -05:00
llava_cpp.py Make building llava optional 2023-11-28 04:55:21 -05:00
py.typed Add py.typed 2023-08-11 09:58:48 +02:00