Revert "[1/2] Optimizations and refactors about quant kernel (#9534)" (#10292)

2025-09-10 18:24:23 -07:00
parent 033b75f559
commit 6d55f60e77
11 changed files with 328 additions and 995 deletions
--- a/sgl-kernel/python/sgl_kernel/init.py
+++ b/sgl-kernel/python/sgl_kernel/init.py
@@ -58,7 +58,8 @@ from sgl_kernel.gemm import (
    scaled_fp4_grouped_quant,
    scaled_fp4_quant,
    sgl_per_tensor_quant_fp8,
-    sgl_per_token_group_quant_8bit,
+    sgl_per_token_group_quant_fp8,
+    sgl_per_token_group_quant_int8,
    sgl_per_token_quant_fp8,
    shuffle_rows,
    silu_and_mul_scaled_fp4_grouped_quant,