@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
attention
core
cpu
cutlass_extensions
libtorch_stable
moe
quantization
quickreduce
rocm
cache.h
cuda_compat.h
cuda_utils.h
cumem_allocator.cpp
cumem_allocator_compat.h
custom_all_gather_reduce_scatter.cuh
custom_all_reduce.cuh
custom_collective_common.cuh
custom_quickreduce.cu
dispatch_utils.h
flashkda_registration.cpp
fs_io.cpp
ops.h
qutlass_registration.cpp
spinloop.cpp
torch_bindings.cpp
torch_utils.h