Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
change
sglang
Commits
de2faef9
Unverified
Commit
de2faef9
authored
May 02, 2025
by
Ke Bao
Committed by
GitHub
May 01, 2025
Browse files
Remove extra contiguous (#5953)
parent
67b7d5b1
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
python/sglang/srt/models/deepseek_v2.py
python/sglang/srt/models/deepseek_v2.py
+1
-1
No files found.
python/sglang/srt/models/deepseek_v2.py
View file @
de2faef9
...
@@ -752,7 +752,7 @@ class DeepseekV2AttentionMLA(nn.Module):
...
@@ -752,7 +752,7 @@ class DeepseekV2AttentionMLA(nn.Module):
q_nope_out
=
q_nope_out
.
transpose
(
0
,
1
)
q_nope_out
=
q_nope_out
.
transpose
(
0
,
1
)
k_nope
=
latent_cache
[...,
:
self
.
kv_lora_rank
]
k_nope
=
latent_cache
[...,
:
self
.
kv_lora_rank
]
k_nope
=
self
.
kv_a_layernorm
(
k_nope
.
contiguous
()
).
unsqueeze
(
1
)
k_nope
=
self
.
kv_a_layernorm
(
k_nope
).
unsqueeze
(
1
)
k_pe
=
latent_cache
[...,
self
.
kv_lora_rank
:].
unsqueeze
(
1
)
k_pe
=
latent_cache
[...,
self
.
kv_lora_rank
:].
unsqueeze
(
1
)
q_pe
,
k_pe
=
self
.
rotary_emb
(
positions
,
q_pe
,
k_pe
)
q_pe
,
k_pe
=
self
.
rotary_emb
(
positions
,
q_pe
,
k_pe
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment