DP Enhancement (#8280)

This commit is contained in:
Cheng Wan
2025-07-24 21:36:21 -07:00
committed by GitHub
parent 28d4d47280
commit c0fb25e949
20 changed files with 665 additions and 1116 deletions

View File

@@ -12,14 +12,16 @@
# limitations under the License.
# ==============================================================================
"""Radix attention."""
from __future__ import annotations
from enum import Enum
from typing import Optional
from typing import TYPE_CHECKING, Optional
from torch import nn
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.model_executor.forward_batch_info import ForwardBatch
if TYPE_CHECKING:
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.model_executor.forward_batch_info import ForwardBatch
class AttentionType(Enum):