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 10, 19:00 UTC
[Bugfix] Fix AttributeError: 'Stream' object has no attribute 'dp_size' (#31663)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Jee Jee Li committed
Jan 5, 2026 at 10:31 UTC
f099cd557a82f62f5368904d15f39d4dd672e6e9
1 file changed
-1
vllm/lora/layers/fused_moe.py
-1
@@ -130,7 +130,6 @@ class FusedMoEWithLoRA(BaseLayerWithLoRA):
130
prepare_finalize, self.base_layer
131
),
132
self.base_layer.shared_experts,
133
- getattr(self.base_layer, "shared_experts_stream", None),
133
)
134
if quant_config.use_mxfp4_w4a16:
135
assert isinstance(