https://pypi.org/project/hugpy-wrapper/ Recent updates to the Python Package Index for hugpy-wrapper en https://pypi.org/project/hugpy-wrapper/0.1.5/ The hugpy wrapper (import name: fitevict): a per-box evict-to-fit front door. An OpenAI /v1 server that resolves a called model to its weights (GGUF via llama.cpp, or transformers), places it on the GPU by evicting what doesn't fit, serves it, and logs every call. support@hugpy.ai Sun, 04 Oct 2026 05:24:05 GMT https://pypi.org/project/hugpy-wrapper/0.1.4/ The hugpy wrapper (import name: fitevict): a per-box evict-to-fit front door. An OpenAI /v1 server that resolves a called model to its weights (GGUF via llama.cpp, or transformers), places it on the GPU by evicting what doesn't fit, serves it, and logs every call. support@hugpy.ai Sun, 04 Oct 2026 04:31:28 GMT https://pypi.org/project/hugpy-wrapper/0.1.3/ The hugpy wrapper (import name: fitevict): a per-box evict-to-fit front door. An OpenAI /v1 server that resolves a called model to its weights (GGUF via llama.cpp, or transformers), places it on the GPU by evicting what doesn't fit, serves it, and logs every call. support@hugpy.ai Sun, 04 Oct 2026 04:03:31 GMT https://pypi.org/project/hugpy-wrapper/0.1.2/ The hugpy wrapper (import name: fitevict): a per-box evict-to-fit front door. An OpenAI /v1 server that resolves a called model to its weights (GGUF via llama.cpp, or transformers), places it on the GPU by evicting what doesn't fit, serves it, and logs every call. support@hugpy.ai Sun, 04 Oct 2026 01:49:20 GMT https://pypi.org/project/hugpy-wrapper/0.1.1/ The hugpy wrapper (import name: fitevict): a per-box evict-to-fit front door. An OpenAI /v1 server that resolves a called model to its weights (GGUF via llama.cpp, or transformers), places it on the GPU by evicting what doesn't fit, serves it, and logs every call. support@hugpy.ai Sun, 04 Oct 2026 01:30:19 GMT https://pypi.org/project/hugpy-wrapper/0.1.0/ The hugpy wrapper (import name: fitevict): a per-box evict-to-fit front door. An OpenAI /v1 server that resolves a called model to its weights (GGUF via llama.cpp, or transformers), places it on the GPU by evicting what doesn't fit, serves it, and logs every call. support@hugpy.ai Sat, 03 Oct 2026 21:48:36 GMT