Large Language Model Inference & Deployment
13 repos
Python-based tools and frameworks for running, serving, and interacting with large language models locally and at scale. This cluster spans inference engines (Ollama, MaxText), model adaptation layers (LLaMa2lang, enchanted), and client libraries across multiple platforms including Swift mobile bindings. The repositories focus on making LLMs practical for deployment—whether through optimization, containerization, or accessible APIs—with particular emphasis on open models like Llama and Mistral.
Python · 7
Swift · 3
JavaScript · 2
Go · 1
llm ·198,298
mistral ·197,927
ollama ·195,134
llama ·192,767
llama3 ·186,428
gemma3 ·182,685
deepseek ·182,685
llms ·182,182
gemma ·180,647
golang ·180,272
