This commit is contained in:
RandNMR73
2026-04-09 05:34:20 +00:00
parent 43d277e13c
commit 3fd5502d90
50 changed files with 141 additions and 166 deletions
@@ -9,7 +9,7 @@ import triton.language as tl
from triton.tools.tensor_descriptor import TensorDescriptor
from .quant_utils import fake_quantize_q, fake_quantize_kv, fake_quantize
# from modified_sageattn.api import triton_group_mean
# from attn_qat_infer.api import triton_group_mean
def is_cuda():