vllm/csrc/moe/marlin_kernels at 098f94de42859f8251fe920f87adb88336129c53 - vllm

mirror of https://github.com/wassname/vllm.git synced 2026-07-06 05:17:51 +08:00

Files

T

ElizaWszola 05d686432f [Kernel] Zero point support in fused MarlinMoE kernel + AWQ Fused MoE (#8973 )

Co-authored-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika Sikka <ds3822@columbia.edu>

2024-10-04 12:34:44 -06:00

marlin_moe_kernel_ku4.cu

2024-10-04 12:34:44 -06:00

marlin_moe_kernel_ku4.h

2024-10-04 12:34:44 -06:00

marlin_moe_kernel_ku4b8.cu

2024-10-04 12:34:44 -06:00

marlin_moe_kernel_ku4b8.h

2024-10-04 12:34:44 -06:00

marlin_moe_kernel_ku8b128.cu

2024-10-04 12:34:44 -06:00

marlin_moe_kernel_ku8b128.h

2024-10-04 12:34:44 -06:00

marlin_moe_kernel.h

2024-10-04 12:34:44 -06:00