Categories / LLM Infrastructure
raketenkater / ggrun
llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.
Last push 7 hours ago
cuda
gguf
golang
inference-server
llama-cpp
llamacpp
llm
local-llm
localllama
metal
moe
multi-gpu
ollama-alternative
openai-api
self-hosted
speculative-decoding
vulkan
Created
Mar 2026
Total stars
284
Last 7 days
+1
Last 30 days
+3
Last 12 months
+284
README badge
[](https://bestofgo.dev/raketenkater/ggrun)