Popular repositories Loading

1. llama-turboquant llama-turboquant Public

   Forked from animehacker/llama-turboquant

   TurboQuant for GGML: 4.57x KV Cache Compression with 72K+ Context for Llama-3.3-70B on Consumer GPUs.

   C++

2. OpenArc OpenArc Public

   Forked from SearchSavior/OpenArc

   Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS, Embedding and Rerank models over OpenAI endpoints.

   Python