gpu-offload

Here are 4 public repositories matching this topic...

Qwen3.8 Flash Next FP8 on 4x CMP 170HX: PP3 transformer stages with the 51B PLE table on GPU 3

vllm qwen pipeline-parallel gpu-offload cmp170hx qwen3-8

Experimental portable GGML GPU offload for diffuse-cpp across Vulkan, Metal, and CUDA

metal vulkan cuda ggml diffusion-language-models gpu-offload

Proof repo: run a real LLM fully on-device in React Native (Expo + llama.rn). Offline, no cloud, sub-2s cold start.

react-native flutter rag npu edge-ai on-device-ai mobile-ai llm llama-cpp genai offline-ai private-ai gpu-offload

Bash script for 72B LLM testing on Tesla P40 with RTX 3050 offload

bash cuda llm llama-cpp gguf tesla-p40 rtx-3050 gpu-offload

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