Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
C
Merge dev into fix/windows-qwen36-cuda-dll: keep dev's qwen36 prerequisites plus the alias and .build-config
JustVugg9fc4ca37e2d6
diff --cc c/Makefileindex 774d43ba,d8663ad7..4ee30e26--- a/c/Makefile+++ b/c/Makefile@@@ -1117,7 -1072,15 +1117,15 @@@ QWEN36_TIER_SRCQWEN36_CFLAGS = $(NOCUDA_CFLAGS)QWEN36_LDFLAGS = $(NOCUDA_LDFLAGS)endif- qwen36$(EXE): qwen36.c decode_batch.h serve_poll.h cli_args.h qwen36_tier.h expert_ffn.h idot.h st.h json.h compat.h omp_tune.h kv_prefix.h pin_pool.h edge_adapter_internal.h edge_adapters.h edge_runtime.h segment_adapter_internal.h segment_adapters.h segment_runtime.h gsgemv.h qgemv.h $(QWEN36_TIER_SRC) $(CUDA_OBJ)+ # On Windows, EXE=.exe. Keep a bare qwen36 target so GNU make does not+ # fall through to its implicit %: %.c rule and compile qwen36.c alone.+ ifneq ($(EXE),)+ .PHONY: qwen36+ qwen36: qwen36$(EXE)+ endif+ # Rebuild when CUDA_DLL changes; otherwise an existing CPU-only executable can+ # be reported as up to date despite selecting the Windows CUDA DLL tier.-qwen36$(EXE): qwen36.c serve_poll.h cli_args.h qwen36_tier.h expert_ffn.h st.h json.h compat.h omp_tune.h kv_prefix.h edge_adapter_internal.h edge_adapters.h edge_runtime.h segment_adapter_internal.h segment_adapters.h segment_runtime.h $(QWEN36_TIER_SRC) $(CUDA_OBJ) .build-config++qwen36$(EXE): qwen36.c decode_batch.h serve_poll.h cli_args.h qwen36_tier.h expert_ffn.h idot.h st.h json.h compat.h omp_tune.h kv_prefix.h pin_pool.h edge_adapter_internal.h edge_adapters.h edge_runtime.h segment_adapter_internal.h segment_adapters.h segment_runtime.h gsgemv.h qgemv.h $(QWEN36_TIER_SRC) $(CUDA_OBJ) .build-config$(CC) $(QWEN36_CFLAGS) qwen36.c $(QWEN36_TIER_SRC) $(CUDA_OBJ) -o qwen36$(EXE) $(QWEN36_LDFLAGS)# DeepSeek V4.1 Flash: one file, like every other portable engine. The fp4 experts