Pinned Loading
-
agentica
agentica PublicAgentic ProHarness: A multi-agent, self-improving programming system that autonomously plans, writes, tests, debugs, and learns from every iteration — powered entirely by local llm models on consum…
Python
-
triattention_nf4
triattention_nf4 PublicTriAttention KV Cache Compression for NF4 Models. Full implementation of TriAttention (arxiv:2604.04921) for NF4-quantized HuggingFace transformer models using bitsandbytes.
Python
-
turboquant
turboquant PublicStandalone TurboQuant KV Cache Inference for https://huggingface.co/g023/Qwen3-1.77B-g023
Python 4
-
g023-OllamaMan
g023-OllamaMan PublicA Concept Ollama Server Management OS that runs in a web browser.
PHP 7
-
If the problem persists, check the GitHub status page or contact support.
