Popular repositories Loading

1. plot_curves plot_curves Public

   Python 1

2. llm-vram-calculator llm-vram-calculator Public

   Free LLM VRAM calculator core behind modelvram.com: GPU memory for weights, KV cache and overhead of any Hugging Face model. MoE, MLA, sliding windows, GGUF; checked against public llama.cpp and vL…

   TypeScript 1

3. WaRPQ WaRPQ Public

   Python

4. mt-rbac mt-rbac Public

   Java

5. model_inference model_inference Public

   模型推理框架，仿vllm

   Python

6. orion orion Public

   Forked from eth-easl/orion

   支持cuda12.x的orion

   Python