A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 3, 16:30 UTC
[Fix] Weight loading for qwen3_5 using runai_streamer (#42521)
Signed-off-by: Harsh Shah <iharsh@google.com> Co-authored-by: Harsh Shah <iharsh@google.com>
Harsh Shah committed
May 14, 2026 at 08:06 UTC
ca60a4e84f9a8713617c211885d553ba10204f59
1 file changed
+2
-2
vllm/model_executor/models/qwen3_5.py
+2
-2
@@ -262,8 +262,8 @@ class Qwen3_5Model(Qwen3NextModel):
262
param,
263
curr_expert_weight,
264
name,
265
- shard_id,
266
- expert_id,
265
+ shard_id=shard_id,
266
+ expert_id=expert_id,
267
return_success=True,
268
)
269
if success: