[Qwen-moe] Remove the minor operation arange (#2373)
### What this PR does / why we need it?
Integrate the arange operator to reduce the time spent and improve
performance
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.10.1.1
- vLLM main:
56dcf4e7e9
---------
Signed-off-by: s30076806 <songjiayang2@h-partners.com>
This commit is contained in:
@@ -405,7 +405,7 @@ class TestExpertsSelector:
|
||||
|
||||
x = torch.randn(8, 2)
|
||||
router_logits = torch.randn(8, 2)
|
||||
topk_weights, topk_ids = select_experts(
|
||||
topk_weights, topk_ids, _ = select_experts(
|
||||
hidden_states=x,
|
||||
router_logits=router_logits,
|
||||
top_k=2,
|
||||
|
||||
Reference in New Issue
Block a user