biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Kernel] Update cutlass_scaled_mm to support 2d group (blockwise) scaling (#11868)

Browse Source
This commit is contained in:
Lucas Wilkinson
2025-01-30 21:33:00 -05:00
committed by GitHub
parent 4078052f09
commit 9798b2fb00
25 changed files with 1924 additions and 346 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
csrc/quantization/cutlass_w8a8/scaled_mm_entry.cu
View File

@@ -89,15 +89,12 @@ void cutlass_scaled_mm(torch::Tensor& c, torch::Tensor const& a,
TORCH_CHECK(a.dim() == 2 && b.dim() == 2 && c.dim() == 2);
TORCH_CHECK(c.size(0) == a.size(0) && a.size(1) == b.size(0) &&
b.size(1) == c.size(1));
TORCH_CHECK(a_scales.numel() == 1 || a_scales.numel() == a.size(0));
TORCH_CHECK(b_scales.numel() == 1 || b_scales.numel() == b.size(1));
// Check for strides and alignment
TORCH_CHECK(a.stride(1) == 1 && c.stride(1) == 1); // Row-major
TORCH_CHECK(b.stride(0) == 1); // Column-major
TORCH_CHECK(c.stride(0) % 16 == 0 &&
b.stride(1) % 16 == 0); // 16 Byte Alignment
TORCH_CHECK(a_scales.is_contiguous() && b_scales.is_contiguous());
if (bias) {
TORCH_CHECK(bias->numel() == b.size(1) && bias->is_contiguous() &&