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
9279c59a
Unverified
Commit
9279c59a
authored
Mar 19, 2026
by
bnellnm
Committed by
GitHub
Mar 19, 2026
Browse files
[MoE Refactor] DefaultMoERunner simplifcation (#33049)
Signed-off-by:
Bill Nell
<
bnell@redhat.com
>
parent
74540961
Changes
2
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
379 additions
and
295 deletions
+379
-295
vllm/model_executor/layers/fused_moe/layer.py
vllm/model_executor/layers/fused_moe/layer.py
+2
-0
vllm/model_executor/layers/fused_moe/runner/default_moe_runner.py
...el_executor/layers/fused_moe/runner/default_moe_runner.py
+377
-295
No files found.
vllm/model_executor/layers/fused_moe/layer.py
View file @
9279c59a
...
...
@@ -504,6 +504,8 @@ class FusedMoE(CustomOp):
self
.
apply_router_weight_on_input
=
apply_router_weight_on_input
self
.
activation
=
MoEActivation
.
from_str
(
activation
)
# TODO(bnell): we should not have to create a router if the kernel is
# monolithic.
self
.
router
=
create_fused_moe_router
(
top_k
=
top_k
,
global_num_experts
=
self
.
global_num_experts
,
...
...
vllm/model_executor/layers/fused_moe/runner/default_moe_runner.py
View file @
9279c59a
This diff is collapsed.
Click to expand it.
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