tools - vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

0 0 1 Python

	ep_kernels
	pre_commit
	profiler
	vllm-rocm
	vllm-tpu
	check_repo.sh	336 B
	flashinfer-build.sh	2.0 KB
	generate_cmake_presets.py	6.2 KB
	generate_versions_json.py	4.1 KB
	install_deepgemm.sh	3.8 KB
	install_gdrcopy.sh	1.4 KB
	install_nixl_from_source_ubuntu.py	8.8 KB
	install_torchcodec_rocm.sh	3.0 KB
	report_build_time_ninja.py	13.3 KB