Misc clean up; Remove the support of jump forward (#4032)

2025-03-03 07:02:14 -08:00
parent 110e006673
commit 935cda944b
41 changed files with 396 additions and 426 deletions
--- a/python/sglang/srt/layers/quantization/modelopt_quant.py
+++ b/python/sglang/srt/layers/quantization/modelopt_quant.py
@@ -12,7 +12,7 @@ from vllm.model_executor.layers.quantization.utils.w8a8_utils import (
    requantize_with_max_scale,
 )

-from sglang.srt.layers.attention import AttentionBackend
+from sglang.srt.layers.attention.base_attn_backend import AttentionBackend
 from sglang.srt.layers.linear import LinearBase, LinearMethodBase
 from sglang.srt.layers.parameter import ModelWeightParameter, PerTensorScaleParameter
 from sglang.srt.layers.quantization.base_config import (