git
ask
hub
Privacy
Terms
Sign in with GitHub
borisk1/llama.cpp-fusion
↗
Stars ·
2
Language ·
C++
License ·
MIT
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: borisk1
Ask anything about this repo to start.
Help me pick thread-copy CPU core groups for my dual Xeon server using numactl output.
Explain how to enable the MoE Cache with GGML_CUDA_MOE_CACHE and set a VRAM budget.
Walk me through offloading a large DeepSeek model across 4 GPUs with this fork.
Show me the cpu-moe flag for running MoE experts on CPU while attention runs on GPU.
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).