update directory for cutlass w8a8

Browse Source

Signed-off-by: yewentao256 <zhyanwentao@126.com>

...

This commit is contained in:

yewentao256

2025-08-27 21:05:41 +00:00

parent c643e63f98

commit 57f2f26a05

42 changed files with 22 additions and 22 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

0

csrc/quantization/cutlass_w8a8/Epilogues.md → csrc/quantization/w8a8/cutlass/Epilogues.md

0

csrc/quantization/cutlass_w8a8/c3x/cutlass_gemm_caller.cuh → csrc/quantization/w8a8/cutlass/c3x/cutlass_gemm_caller.cuh

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm.cuh → csrc/quantization/w8a8/cutlass/c3x/scaled_mm.cuh

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_azp_sm90_int8.cu → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_azp_sm90_int8.cu

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_blockwise_sm100_fp8.cu → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm100_fp8.cu

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_blockwise_sm100_fp8_dispatch.cuh → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm100_fp8_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_blockwise_sm120_fp8.cu → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm120_fp8.cu

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_blockwise_sm120_fp8_dispatch.cuh → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm120_fp8_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_blockwise_sm90_fp8.cu → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm90_fp8.cu

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_blockwise_sm90_fp8_dispatch.cuh → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm90_fp8_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_helper.hpp → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_helper.hpp

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_kernels.hpp → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_kernels.hpp

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm100_fp8.cu → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm100_fp8.cu

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm100_fp8_dispatch.cuh → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm100_fp8_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm120_fp8.cu → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm120_fp8.cu

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm120_fp8_dispatch.cuh → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm120_fp8_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm90_fp8.cu → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm90_fp8.cu

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm90_fp8_dispatch.cuh → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm90_fp8_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm90_int8.cu → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm90_int8.cu

0

csrc/quantization/cutlass_w8a8/c3x/scaled_mm_sm90_int8_dispatch.cuh → csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm90_int8_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/moe/blockwise_scaled_group_mm_sm100.cu → csrc/quantization/w8a8/cutlass/moe/blockwise_scaled_group_mm_sm100.cu

0

csrc/quantization/cutlass_w8a8/moe/get_group_starts.cuh → csrc/quantization/w8a8/cutlass/moe/get_group_starts.cuh

0

csrc/quantization/cutlass_w8a8/moe/grouped_mm_c3x.cuh → csrc/quantization/w8a8/cutlass/moe/grouped_mm_c3x.cuh

0

csrc/quantization/cutlass_w8a8/moe/grouped_mm_c3x_sm100.cu → csrc/quantization/w8a8/cutlass/moe/grouped_mm_c3x_sm100.cu

0

csrc/quantization/cutlass_w8a8/moe/grouped_mm_c3x_sm90.cu → csrc/quantization/w8a8/cutlass/moe/grouped_mm_c3x_sm90.cu

0

csrc/quantization/cutlass_w8a8/moe/moe_data.cu → csrc/quantization/w8a8/cutlass/moe/moe_data.cu

0

csrc/quantization/cutlass_w8a8/scaled_mm_c2x.cu → csrc/quantization/w8a8/cutlass/scaled_mm_c2x.cu

0

csrc/quantization/cutlass_w8a8/scaled_mm_c2x.cuh → csrc/quantization/w8a8/cutlass/scaled_mm_c2x.cuh

0

csrc/quantization/cutlass_w8a8/scaled_mm_c2x_sm75_dispatch.cuh → csrc/quantization/w8a8/cutlass/scaled_mm_c2x_sm75_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/scaled_mm_c2x_sm80_dispatch.cuh → csrc/quantization/w8a8/cutlass/scaled_mm_c2x_sm80_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/scaled_mm_c2x_sm89_fp8_dispatch.cuh → csrc/quantization/w8a8/cutlass/scaled_mm_c2x_sm89_fp8_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/scaled_mm_c2x_sm89_int8_dispatch.cuh → csrc/quantization/w8a8/cutlass/scaled_mm_c2x_sm89_int8_dispatch.cuh

0

csrc/quantization/cutlass_w8a8/scaled_mm_c3x_sm100.cu → csrc/quantization/w8a8/cutlass/scaled_mm_c3x_sm100.cu

0

csrc/quantization/cutlass_w8a8/scaled_mm_c3x_sm120.cu → csrc/quantization/w8a8/cutlass/scaled_mm_c3x_sm120.cu

0

csrc/quantization/cutlass_w8a8/scaled_mm_c3x_sm90.cu → csrc/quantization/w8a8/cutlass/scaled_mm_c3x_sm90.cu

0

csrc/quantization/cutlass_w8a8/scaled_mm_entry.cu → csrc/quantization/w8a8/cutlass/scaled_mm_entry.cu

0

csrc/quantization/8bit/fp8/per_token_group_quant.cu → csrc/quantization/w8a8/fp8/per_token_group_quant.cu

0

csrc/quantization/8bit/int8/per_token_group_quant.cu → csrc/quantization/w8a8/int8/per_token_group_quant.cu

0

csrc/quantization/8bit/int8/scaled_quant.cu → csrc/quantization/w8a8/int8/scaled_quant.cu

0

csrc/quantization/8bit/per_token_group_quant_8bit.h → csrc/quantization/w8a8/per_token_group_quant_8bit.h