aparler/c-llm
1
0
Fork 0
mirror of https://github.com/karpathy/llm.c.git synced 2026-07-28 20:35:09 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

Build changes

Browse source
This commit is contained in:
mpragnay 2025-12-06 21:45:17 -05:00
parent 07049a62eb
commit de1f17078e
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
Makefile
View file

@ -304,10 +304,10 @@ test_nvshmem: test_nvshmem_basic.cu
# Run with: NVSHMEM_BOOTSTRAP=MPI mpirun -np 2 ./nvshmem_train_gpt2 -b 4 -t 128
nvshmem_train_gpt2: nvshmem_train_gpt2.cu
$(NVCC) --threads=0 -t=0 --use_fast_math -std=c++17 -O3 \
-arch=sm_80 \
-arch=sm_80 -rdc=true --extended-lambda --expt-relaxed-constexpr \
-I$(NVSHMEM_HOME)/include -L$(NVSHMEM_HOME)/lib \
-I$(OPENMPI_INCLUDE_PATH) -L$(OPENMPI_LIB_PATH) \
$^ -lnvshmem -lcublas -lcublasLt -lcudart -lnvidia-ml -lmpi $(CUDA_OUTPUT_FILE)
$^ -lnvshmem_host -lnvshmem_device -lcublas -lcublasLt -lcuda -lcudart -lnvidia-ml -lmpi $(CUDA_OUTPUT_FILE)
clean: