Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
5d043c16
Unverified
Commit
5d043c16
authored
Mar 13, 2025
by
Kyle Sayers
Committed by
GitHub
Mar 13, 2025
Browse files
[Quant] Bamba SupportsQuant (#14698)
Signed-off-by:
Kyle Sayers
<
kylesayrs@gmail.com
>
parent
36d1ccb2
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
2 deletions
+2
-2
vllm/model_executor/models/bamba.py
vllm/model_executor/models/bamba.py
+2
-2
No files found.
vllm/model_executor/models/bamba.py
View file @
5d043c16
...
...
@@ -33,7 +33,7 @@ from vllm.sequence import IntermediateTensors
from
vllm.utils
import
LayerBlockType
from
.interfaces
import
(
HasInnerState
,
IsHybrid
,
SupportsLoRA
,
SupportsPP
,
SupportsV0Only
)
SupportsQuant
,
SupportsV0Only
)
from
.utils
import
(
is_pp_missing_parameter
,
make_empty_intermediate_tensors_factory
,
make_layers
,
maybe_prefix
)
...
...
@@ -367,7 +367,7 @@ class BambaModel(nn.Module):
class
BambaForCausalLM
(
nn
.
Module
,
HasInnerState
,
SupportsLoRA
,
SupportsPP
,
IsHybrid
,
SupportsV0Only
):
IsHybrid
,
SupportsV0Only
,
SupportsQuant
):
packed_modules_mapping
=
{
"qkv_proj"
:
[
"q_proj"
,
...
...
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