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

2025-09-05 18:45:08 +08:00
parent afd9f2f560
commit 339f8eef09
11 changed files with 996 additions and 329 deletions
--- a/sgl-kernel/python/sgl_kernel/init.py
+++ b/sgl-kernel/python/sgl_kernel/init.py
@@ -55,8 +55,7 @@ from sgl_kernel.gemm import (
    scaled_fp4_grouped_quant,
    scaled_fp4_quant,
    sgl_per_tensor_quant_fp8,
-    sgl_per_token_group_quant_fp8,
-    sgl_per_token_group_quant_int8,
+    sgl_per_token_group_quant_8bit,
    sgl_per_token_quant_fp8,
    shuffle_rows,
    silu_and_mul_scaled_fp4_grouped_quant,