[Kernel] Zero point support in fused MarlinMoE kernel + AWQ Fused MoE (…

…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>
compressa-ai · Oct 26, 2024 · 35e10d6 · 35e10d6
1 parent ec7933f
commit 35e10d6
Show file tree

Hide file tree

Showing 23 changed files with 969 additions and 223 deletions.
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -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(