Add missing assertion in NemotronH path (#15193)

Signed-off-by: Roi Koren <roik@nvidia.com>
This commit is contained in:
roikoren755
2025-12-15 16:17:21 +02:00
committed by GitHub
parent 3518b33178
commit 9003a4369d

View File

@@ -1266,6 +1266,9 @@ class ServerArgs:
)
self.disable_radix_cache = True
elif model_arch in ["NemotronHForCausalLM"]:
assert (
not self.enable_mamba_extra_buffer()
), f"mamba extra_buffer is not supported for {model_arch} model"
model_config = self.get_model_config()
if model_config.quantization in [
"modelopt",