minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Delete CUTLASS FP8 blockwise for SM90 and SM100, move SM120 to JIT and add SwapAB (#30438)

Browse Source 
Co-authored-by: Brayden Zhong <brayden.zhong@radixark.ai>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: root <root@sgl-b300-inference.datacrunch.io>
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
This commit is contained in:
Brayden Zhong
2026-07-14 09:31:32 +08:00
committed by GitHub
co-authored by Brayden Zhong Claude Sonnet 5 root Brayden Zhong
parent c124bec99d
commit 7431f35fd8
17 changed files with 765 additions and 1159 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sgl-kernel/include/sgl_kernel_ops.h
-6
View File
@@ -235,12 +235,6 @@ torch::Tensor fp8_scaled_mm(
const torch::Tensor& scales_b,
const torch::Dtype& out_dtype,
const c10::optional<torch::Tensor>& bias);
torch::Tensor fp8_blockwise_scaled_mm(
const torch::Tensor& mat_a,
const torch::Tensor& mat_b,
const torch::Tensor& scales_a,
const torch::Tensor& scales_b,
const torch::Dtype& out_dtype);
void sgl_per_token_group_quant_8bit(
at::Tensor input,
at::Tensor output_q,