Skip to content

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

C

Commits on main

a29c6e6
Merge branch 'dev' into sse41-tier-upstream
Vincenzo Fornaro committed 2 months ago
07886a5
Merge branch 'dev' into feat/windows-xdna-shared-expert-lane
Kenneth-Javier Ortigoza committed 2 months ago
91733b8
Merge dev into feat/qwen38-flash-next
JustVugg committed 2 months ago
fd9b19d
Merge branch 'dev' into upstream/qwen36-int4-unpack
Vincenzo Fornaro committed 2 months ago
ef2cb33
Merge branch 'dev' into fix/qwen36-compiler-warnings-v2
Vincenzo Fornaro committed 2 months ago
ec79720
Merge dev into feat/qwen38-flash-next
JustVugg committed 2 months ago
eabd569
2e7dfa6
7892f58
7b4a236
b3fe3e5
75e0048
e7df0ac
Merge pull request #1268 from JustVugg/dev
Vincenzo Fornaro committed 2 months ago
184e052
2a12e44