Skip to content

update #8359

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wawltor merged 10 commits into from
May 7, 2024
Merged

update #8359

Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
5db1b03
change llama/modeling.py to opt npu performence
wanghuancoder Apr 28, 2024
48a1338
update
wanghuancoder Apr 28, 2024
11a52e0
update
wanghuancoder Apr 28, 2024
f2252e8
Update modeling.py
Galaxy1458 Apr 29, 2024
198e58e
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleNLP i…
wanghuancoder Apr 30, 2024
e557b5a
Merge branch 'develop' of https://github.com/Galaxy1458/PaddleNLP int…
wanghuancoder Apr 30, 2024
672f4aa
add judge
wanghuancoder Apr 30, 2024
b8f7868
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleNLP i…
Galaxy1458 May 5, 2024
8810249
update
Galaxy1458 May 5, 2024
4c404d7
update
Galaxy1458 May 7, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions paddlenlp/transformers/llama/modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ def swiglu(x, y=None):
"LlamaForCausalLM",
"LlamaPretrainingCriterion",
]

global npu_is_casual
npu_is_casual = False

def _get_interleave(n):
Expand Down Expand Up @@ -213,7 +213,7 @@ def scaled_dot_product_attention(
):
bsz, q_len, num_heads, head_dim = query_states.shape
_, kv_seq_len, _, _ = value_states.shape

global npu_is_casual
if config.use_flash_attention and flash_attention:
# Paddle Flash Attention input [ bz, seqlen, nhead, head_dim]
# Torch Flash Attention input [ bz, nhead, seqlen, head_dim]
Expand Down Expand Up @@ -1613,6 +1613,7 @@ def forward(
attention_mask = self._prepare_decoder_attention_mask(
attention_mask, (batch_size, seq_length), cache_length, inputs_embeds.dtype
) # [bs, 1, seq_len, seq_len]
global npu_is_casual
if self.config.use_flash_attention:
is_casual = is_casual_mask(attention_mask)
if get_env_device() != "npu":
Expand Down