(self, hidden_states, lora_layer_params=None)
| 1695 | self.register_parameter('clamp_val', None) |
| 1696 | |
| 1697 | def forward(self, hidden_states, lora_layer_params=None): |
| 1698 | assert lora_layer_params is None, f"lora is not supported on {self.__class__.__name__} now" |
| 1699 | inter = self.fc(hidden_states) |
| 1700 | inter = ACT2FN[self.hidden_act](inter) |
| 1701 | if self.quant_mode.has_fp8_rowwise(): |
| 1702 | # Quantize per token outputs tuple: |
| 1703 | # quantized tensor and scaling factors per token |
| 1704 | clamp_val = None if self.clamp_val is None else self.clamp_val.value |
| 1705 | inter = quantize_fp8_per_token(inter, clamp_val) |
| 1706 | output = self.proj(inter) |
| 1707 | return output |
| 1708 | |
| 1709 | |
| 1710 | class Fp8RowwiseGatedMLP(Fp8RowwiseMLP): |
nothing calls this directly
no test coverage detected