gpu-memory

Here are 2 public repositories matching this topic...

A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology

linux libraries nvidia gpu-memory kernel-mode-driver gpudirect-rdma

H100 LLM KV eval: cuMem 2MiB leaf pack (42% VRAM @70%) + vLLM 0.21 TurboQuant 4bit KV (-58% bytes, ~0.86x decode). Eval-only repro.

cuda inference memory-allocator gpu-memory nvidia-gpu kv-cache long-context vllm llm-inference h100 qwen paged-attention turboquant composable-kv cumem moon-xq

Add a description, image, and links to the gpu-memory topic page so that developers can more easily learn about it.

To associate your repository with the gpu-memory topic, visit your repo's landing page and select "manage topics."