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 8, 08:45 UTC
[Bugfix] Remove assert that's no longer valid (#34443)
Signed-off-by: Bill Nell <bnell@redhat.com>
bnellnm committed
Feb 12, 2026 at 21:18 UTC
04ea31baabc6f5be6b0afd88541f569a4c771ab9
1 file changed
-1
vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py
-1
@@ -37,7 +37,6 @@ class FusedMoEModularMethod(FusedMoEMethodBase, CustomOp):
37
not self.moe_mk.supports_expert_map(),
38
)
39
self.old_quant_method = old_quant_method
40
- assert not self.old_quant_method.is_monolithic
40
logger.debug("Swapping out %s", self.old_quant_method.__class__.__name__)
41
42
@staticmethod