llm_gpu_toolkit
LLM GPU Toolkit: estimate VRAM, training/inference GPU needs, multi-GPU allocation, and quantization impact. 大模型 GPU 显存与算力估算。by jammyfu / PaintingCoder
- 3
- TypeScript
- 5 d ago
LLM GPU Toolkit: estimate VRAM, training/inference GPU needs, multi-GPU allocation, and quantization impact. 大模型 GPU 显存与算力估算。by jammyfu / PaintingCoder
Paste a HF model id, get VRAM for any quant and context
Runs in the browser on Hugging Face
Memory-efficient full-parameter GRPO on a single GPU with phase-aware offloading, CPU AdamW, and async gradient streaming.