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

fixup: keep Windows in the torch pin — +cpu wheels exist there too

JustVuggf03bcea13a22
diff --git a/c/tools/requirements-deepseek-v4-tiny.txt b/c/tools/requirements-deepseek-v4-tiny.txt
index 4e4c6686..e5f084d8 100644
--- a/c/tools/requirements-deepseek-v4-tiny.txt
+++ b/c/tools/requirements-deepseek-v4-tiny.txt
@@ -1,8 +1,8 @@
--extra-index-url https://download.pytorch.org/whl/cpu
-# The +cpu local-version tag exists only in the Linux wheels of the CPU index;
-# macOS wheels are CPU-only by construction and carry the plain version.
-# Same pin either way -- the environment markers pick the spelling per OS.
-torch==2.13.0+cpu; sys_platform == "linux"
+# The +cpu local-version tag exists in the Linux and Windows wheels of the CPU
+# index; macOS wheels are CPU-only by construction and carry the plain
+# version. Same pin either way -- the marker picks the spelling per OS.
+torch==2.13.0+cpu; sys_platform != "darwin"
torch==2.13.0; sys_platform == "darwin"
transformers==5.14.1
safetensors==0.8.0