Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
C
fix(release): package v4_dsml.py so the archived openai_server imports
JustVugg90894cd63cd8
diff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex 54191111..1e570427 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -134,6 +134,7 @@ jobs:cp c/coli dist/cp c/version.py dist/cp c/openai_server.py dist/+ cp c/v4_dsml.py dist/ # openai_server imports v4_dsml (vendored DeepSeek V4 DSML primitives); without it the packaged server won't importcp c/resource_plan.py dist/cp c/doctor.py dist/cp c/autotune.py dist/