vulkan-moe-streaming
akinauphill
Run MoE models several times bigger than your RAM on a gaming PC with an AMD/Vulkan GPU: llama.cpp patch that streams experts from NVMe with a RAM cache and a VRAM hot-expert tier (~2x faster generation, ~7x faster prompts).
Growth over time
1 data points · 2026-10-25 → 2026-10-25How do you feel about this project?
Ask AI about vulkan-moe-streaming
Question copied to clipboardWhat is the akinauphill/vulkan-moe-streaming GitHub project? Description: "Run MoE models several times bigger than your RAM on a gaming PC with an AMD/Vulkan GPU: llama.cpp patch that streams experts from NVMe with a RAM cache and a VRAM hot-expert tier (~2x faster generation, ~7x faster prompts).". Written in Shell. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
🏆 Show off this rank
Add it to a GitHub README or profile — the card updates as the ranking changes:
How to clone vulkan-moe-streaming
Clone via HTTPS
Clone via SSH
Download ZIP
Download main.zipFound an issue?
Report bugs or request features on the vulkan-moe-streaming issue tracker:
Open GitHub Issues