@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
ci
ep_kernels
gumbel_precision
pre_commit
profiler
recipes
vllm-rocm
vllm-tpu
__init__.py
autotune_helion_kernels.py
benchmark_helion_kernels.py
build_deepgemm_C.py
build_rust.py
build_rust.sh
build_triton_from_source.sh
check_repo.sh
check_wheel_deepgemm.py
flashinfer-build.sh
generate_cmake_presets.py
generate_versions_json.py
install_deepgemm.sh
install_gdrcopy.sh
install_nixl_from_source_ubuntu.py
install_snapshot_runtime.sh
install_torchcodec_rocm.sh
install_triton_from_source.sh
report_build_time_ninja.py
setup_deepgemm_pythons.sh
use_existing_torch.py