[Quant][Kernel] Remove GPTQ Group/Dynamic Activation Ordering (#54809)

Signed-off-by: Roderick-Wu <roderickwu2003@gmail.com>
Signed-off-by: Roderick Wu <roderickwu2003@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Roderick Wu
2026-09-08 12:45:12 -07:00
committed by GitHub
co-authored by mgoin
parent 1a522b6949
commit 2c9d68f80b
99 changed files with 1182 additions and 3917 deletions
@@ -47,7 +47,6 @@ def test_choose_mp_linear_kernel_uint4b8():
act_type=torch.float16,
group_size=128,
zero_points=False,
has_g_idx=False,
)
kernel_type = choose_mp_linear_kernel(config)
@@ -65,7 +64,6 @@ def test_choose_mp_linear_kernel_uint4_asymmetric():
act_type=torch.bfloat16,
group_size=64,
zero_points=True,
has_g_idx=False,
)
kernel_type = choose_mp_linear_kernel(config)