Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

support jetson AGX Orin #9109

Closed
wants to merge 4 commits into from
Closed

support jetson AGX Orin #9109

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8672649
support jetson AGX Orin
johnnynunez Oct 6, 2024
3b552f1
Update CMakeLists.txt
johnnynunez Oct 6, 2024
b3be050
Update CMakeLists.txt
johnnynunez Oct 6, 2024
57ca51b
Merge branch 'main' into patch-1
johnnynunez Nov 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ install(CODE "set(CMAKE_INSTALL_LOCAL_ONLY TRUE)" ALL_COMPONENTS)
set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12")

# Supported NVIDIA architectures.
set(CUDA_SUPPORTED_ARCHS "7.0;7.5;8.0;8.6;8.9;9.0")
set(CUDA_SUPPORTED_ARCHS "7.0;7.5;8.0;8.6;8.7;8.9;9.0")

# Supported AMD GPU architectures.
set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101")
Expand Down Expand Up @@ -249,7 +249,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
# Only build Marlin kernels if we are building for at least some compatible archs.
# Keep building Marlin for 9.0 as there are some group sizes and shapes that
# are not supported by Machete yet.
cuda_archs_loose_intersection(MARLIN_ARCHS "8.0;8.6;8.9;9.0" ${CUDA_ARCHS})
cuda_archs_loose_intersection(MARLIN_ARCHS "8.0;8.6;8.7;8.9;9.0" ${CUDA_ARCHS})
if (MARLIN_ARCHS)
set(MARLIN_SRCS
"csrc/quantization/fp8/fp8_marlin.cu"
Expand Down Expand Up @@ -301,7 +301,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
# For the cutlass_scaled_mm kernels we want to build the c2x (CUTLASS 2.x)
# kernels for the remaining archs that are not already built for 3x.
cuda_archs_loose_intersection(SCALED_MM_2X_ARCHS
"7.5;8.0;8.6;8.9;9.0" "${CUDA_ARCHS}")
"7.5;8.0;8.6;8.7;8.9;9.0" "${CUDA_ARCHS}")
# subtract out the archs that are already built for 3x
list(REMOVE_ITEM SCALED_MM_2X_ARCHS ${SCALED_MM_3X_ARCHS})
if (SCALED_MM_2X_ARCHS)
Expand Down Expand Up @@ -427,7 +427,7 @@ set_gencode_flags_for_srcs(
CUDA_ARCHS "${CUDA_ARCHS}")

if(VLLM_GPU_LANG STREQUAL "CUDA")
cuda_archs_loose_intersection(MARLIN_MOE_ARCHS "8.0;8.6;8.9;9.0" "${CUDA_ARCHS}")
cuda_archs_loose_intersection(MARLIN_MOE_ARCHS "8.0;8.6;8.7;8.9;9.0" "${CUDA_ARCHS}")
if (MARLIN_MOE_ARCHS)
set(MARLIN_MOE_SRC
"csrc/moe/marlin_kernels/marlin_moe_kernel.h"
Expand Down