Skip to content

Commit

Permalink
[Kernel] Zero point support in fused MarlinMoE kernel + AWQ Fused MoE (
Browse files Browse the repository at this point in the history
…vllm-project#8973)

Co-authored-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika Sikka <ds3822@columbia.edu>
Signed-off-by: Alvant <alvasian@yandex.ru>
  • Loading branch information
3 people authored and Alvant committed Oct 26, 2024
1 parent ec7933f commit 35e10d6
Show file tree
Hide file tree
Showing 23 changed files with 969 additions and 223 deletions.
2 changes: 2 additions & 0 deletions CMakeLists.txt
Original file line number Diff line number Diff line change
Expand Up @@ -433,6 +433,8 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
"csrc/moe/marlin_kernels/marlin_moe_kernel_ku4b8.cu"
"csrc/moe/marlin_kernels/marlin_moe_kernel_ku8b128.h"
"csrc/moe/marlin_kernels/marlin_moe_kernel_ku8b128.cu"
"csrc/moe/marlin_kernels/marlin_moe_kernel_ku4.h"
"csrc/moe/marlin_kernels/marlin_moe_kernel_ku4.cu"
"csrc/moe/marlin_moe_ops.cu")

set_gencode_flags_for_srcs(
Expand Down
Loading

0 comments on commit 35e10d6

Please sign in to comment.