[Kernel] AQ AZP 3/4: Asymmetric quantization kernels (#7270)
This commit is contained in:
@@ -260,7 +260,7 @@ class QQQLinearMethod(LinearMethodBase):
|
||||
size_k = x_2d.shape[1]
|
||||
size_n = s_ch.shape[1]
|
||||
|
||||
x_int8, s_tok = ops.scaled_int8_quant(x_2d)
|
||||
x_int8, s_tok, _ = ops.scaled_int8_quant(x_2d)
|
||||
|
||||
output_2d = ops.marlin_qqq_gemm(x_int8, qweight, s_tok, s_ch, s_group,
|
||||
workspace, size_m, size_n, size_k)
|
||||
|
||||
Reference in New Issue
Block a user