Remove ScaledActivation for AWQ (#10057)

Signed-off-by: mgoin <michael@neuralmagic.com>
2024-11-06 09:27:06 -05:00
parent 406d4cc480
commit 399c798608
34 changed files with 19 additions and 124 deletions
--- a/vllm/model_executor/models/gpt_bigcode.py
+++ b/vllm/model_executor/models/gpt_bigcode.py
@@ -135,8 +135,7 @@ class GPTBigMLP(nn.Module):
            bias=True,
            quant_config=quant_config,
        )
-        self.act = get_act_fn(config.activation_function, quant_config,
-                              intermediate_size)
+        self.act = get_act_fn(config.activation_function)

    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
        hidden_states, _ = self.c_fc(hidden_states)