A pure C inference engine that runs very large mixture-of-experts models on ordinary hardware by streaming routed experts from disk.
42.7K4.8KCApache-2.0Updated 4 hours ago
#pure-c
Curated GitHub repositories related to pure-c, with AI summaries and key stats.
A pure C inference engine that runs very large mixture-of-experts models on ordinary hardware by streaming routed experts from disk.