Fix grammar abort & Minor style fixes (#7204)
This commit is contained in:
@@ -18,7 +18,6 @@ from typing import Optional
|
||||
|
||||
from torch import nn
|
||||
|
||||
from sglang.srt.layers.linear import UnquantizedLinearMethod
|
||||
from sglang.srt.layers.quantization.base_config import QuantizationConfig
|
||||
from sglang.srt.model_executor.forward_batch_info import ForwardBatch
|
||||
|
||||
@@ -52,9 +51,9 @@ class RadixAttention(nn.Module):
|
||||
sliding_window_size: int = -1,
|
||||
is_cross_attention: bool = False,
|
||||
quant_config: Optional[QuantizationConfig] = None,
|
||||
attn_type=AttentionType.DECODER,
|
||||
prefix: str = "",
|
||||
attn_type: AttentionType = AttentionType.DECODER,
|
||||
use_irope: bool = False,
|
||||
prefix: str = "",
|
||||
):
|
||||
super().__init__()
|
||||
self.tp_q_head_num = num_heads
|
||||
|
||||
Reference in New Issue
Block a user