Add sgl_per_token_quant_fp8 (#4089)

This commit is contained in:
Stefan He
2025-03-06 20:53:05 -08:00
committed by GitHub
parent ad55f17182
commit 63ee26d162
8 changed files with 307 additions and 0 deletions

View File

@@ -106,6 +106,7 @@ sources = [
"src/sgl-kernel/csrc/gemm/fp8_blockwise_gemm_kernel.cu",
"src/sgl-kernel/csrc/gemm/int8_gemm_kernel.cu",
"src/sgl-kernel/csrc/gemm/per_token_group_quant_fp8.cu",
"src/sgl-kernel/csrc/gemm/per_token_quant_fp8.cu",
"src/sgl-kernel/csrc/gemm/per_tensor_quant_fp8.cu",
"src/sgl-kernel/csrc/moe/moe_align_kernel.cu",
"src/sgl-kernel/csrc/speculative/eagle_utils.cu",