Drop torchair (#4814)

aclgraph is stable and fast now. Let's drop torchair graph mode now.

TODO: some logic to adapt torchair should be cleaned up as well. We'll
do it in the following PR.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
This commit is contained in:
wangxiyuan
2025-12-10 09:20:40 +08:00
committed by GitHub
parent ba9cda9dfd
commit 835b4c8f1d
84 changed files with 77 additions and 16881 deletions

View File

@@ -68,9 +68,6 @@ async def test_models(model: str) -> None:
"cudagraph_mode": "FULL_DECODE_ONLY"
}
additional_config: dict[str, Any] = {
"torchair_graph_config": {
"enabled": True
},
"enable_shared_expert_dp": False,
"multistream_overlap_shared_expert": False,
"dynamic_eplb": True,