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

tests: guard -x none on the HIP build

huppiflupp654ff83fd071
diff --git a/c/Makefile b/c/Makefile
index 2a755b48..3ca63b71 100644
--- a/c/Makefile
+++ b/c/Makefile
@@ -984,7 +984,12 @@ cuda-test: backend_cuda.cu backend_cuda.h backend_gpu_compat.h tests/test_backen
# below no longer pulls the runtime, and CI could not catch it because CI
# never runs cuda-test. -Xclang appears nowhere else in CFLAGS.
$(CC) $(filter-out -Xclang -fopenmp,$(CFLAGS)) -fno-openmp -fPIC -c tests/mxfp4_ref.c -o tests/mxfp4_ref.o
- "$(GPUCC)" $(GPUFLAGS) backend_cuda.cu tests/test_mxfp4_cuda.cu -x none tests/mxfp4_ref.o -o mxfp4_cuda_test$(EXE) $(GPU_TEST_LIBS)
+ # -x none only under HIP: hip-test is `$(MAKE) cuda-test HIP=1`, so this
+ # line also runs under nvcc for CUDA users, and nvcc accepts only c, c++
+ # and cu for -x -- it fails the invocation on anything else. CI never
+ # executes cuda-test, so that breakage would surface only on the next
+ # CUDA box to run the suite.
+ "$(GPUCC)" $(GPUFLAGS) backend_cuda.cu tests/test_mxfp4_cuda.cu $(if $(filter 1,$(HIP)),-x none) tests/mxfp4_ref.o -o mxfp4_cuda_test$(EXE) $(GPU_TEST_LIBS)
./mxfp4_cuda_test$(EXE)
# Allocator footprint (#687): what a cudaMalloc really takes off the card,
# which is what the expert tier has to be charged rather than the logical