several fixes

This commit is contained in:
Ashwin Bharambe 2025-04-07 10:31:20 -07:00
parent e2e2820c9a
commit 53a8086e37
60 changed files with 1006 additions and 1078 deletions

View file

@ -4,16 +4,6 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# top-level folder for each specific model found within the models/ directory at
# the top-level of this source tree.
# Copyright (c) Meta Platforms, Inc. and affiliates.
# This software may be used and distributed in accordance with the terms of the Llama 3 Community License Agreement.
import math
from typing import Any, Dict, List, Optional, Tuple
@ -184,7 +174,6 @@ class Attention(nn.Module):
self.head_dim,
)
).cuda()
self.qk_norm = None
if self.use_qk_norm:
self.qk_norm = L2Norm(args.norm_eps)