We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 9ae47b7 commit 7f753d9Copy full SHA for 7f753d9
tensorrt_llm/_torch/models/modeling_gpt_oss.py
@@ -227,7 +227,7 @@ def _create_ideal_expert_load_balanced_logits(
227
228
def compute_gate_output(self, x: torch.Tensor) -> torch.Tensor:
229
if get_sm_version() in [
230
- 90, 100
+ 90, 100, 103
231
] and x.shape[0] <= MIN_LATENCY_TINYGEMM_NUM_TOKENS:
232
weight = self.gate.weight
233
bias = self.gate.bias
0 commit comments