1Soulmate-Halo / heterogeneous-gpu-pd-lab
使用稠密算力卡对稀疏大显存主机进行加速，主机包括 AI Max+ 395、M3 512G、DGX Spark 等。
+104 stars
from 947 · score 4.65
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
4 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2cobanov / PS5LM
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
+82 stars
from 703 · score 4.42
3mozilla-ai / llamafile
Distribute and run LLMs with a single file.
+56 stars
from 26,486 · score 4.04
4heterodoxin / AbliteratedOutTheBox
llama.cpp fork that abliterates at inference
+20 stars
from 142 · score 3.04