chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Revert "[feature] Rework Ascend NPU graph support" (#9385)

Browse Source
This commit is contained in:
Even Zhou
2025-08-20 00:35:10 -07:00
committed by GitHub
parent 1ec9769753
commit de2dd73831
18 changed files with 81 additions and 546 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/models/qwen3.py
+1 -1
View File
@@ -22,8 +22,8 @@ from sglang.srt.layers.radix_attention import RadixAttention
from sglang.srt.layers.rotary_embedding import get_rope
from sglang.srt.layers.utils import PPMissingLayer, get_layer_id
from sglang.srt.layers.vocab_parallel_embedding import ParallelLMHead
from sglang.srt.model_executor.cuda_graph_runner import get_is_capture_mode
from sglang.srt.model_executor.forward_batch_info import ForwardBatch, PPProxyTensors
from sglang.srt.model_executor.graph_runner import get_is_capture_mode
from sglang.srt.model_loader.weight_utils import default_weight_loader
from sglang.srt.models.qwen2 import Qwen2MLP as Qwen3MLP
from sglang.srt.models.qwen2 import Qwen2Model