add sampling_scaling_penalties kernel (#2846)

This commit is contained in:
Xiaoyu Zhang
2025-01-13 11:38:17 +08:00
committed by GitHub
parent c4f9707e16
commit e2b16c4716
9 changed files with 150 additions and 1 deletions

View File

@@ -50,6 +50,7 @@ ext_modules = [
"src/sgl-kernel/csrc/trt_reduce_kernel.cu",
"src/sgl-kernel/csrc/moe_align_kernel.cu",
"src/sgl-kernel/csrc/int8_gemm_kernel.cu",
"src/sgl-kernel/csrc/sampling_scaling_penalties.cu",
"src/sgl-kernel/csrc/sgl_kernel_ops.cu",
],
include_dirs=include_dirs,