Update model_loader deps and qqq quantization deps (#2220) (#2318)

Co-authored-by: HandH1998 <1335248067@qq.com>
2024-12-02 23:22:13 +08:00
parent 33deca81b5
commit 85e1a6f3aa
58 changed files with 2363 additions and 366 deletions
--- a/python/sglang/srt/models/olmo2.py
+++ b/python/sglang/srt/models/olmo2.py
@@ -312,7 +312,6 @@ class Olmo2ForCausalLM(nn.Module):
    def __init__(
        self,
        config: PretrainedConfig,
-        cache_config=None,
        quant_config: Optional[QuantizationConfig] = None,
    ):
        super().__init__()