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

ci: the GLM engines' expert tier on Lavapipe, and under ASan and UBSan

JustVugg2af474c6cbfc
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index d445d75b..ee2ff907 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -175,6 +175,12 @@ jobs:
- family: deepseek
req: c/tools/requirements-deepseek-v4-tiny.txt
extra: sympy pillow # the V4.1 fixture's reference and its vision tower
+ # GLM-5.2 (colibri) and GLM-5.3 Flash (glm53) on the routed-expert tier, and
+ # the same under ASan and UBSan
+ - family: glm
+ req: c/tools/requirements-glm53-tiny.txt
+ - family: glm-sanitize
+ req: c/tools/requirements-glm53-tiny.txt
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5