EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Remove VLLM_USE_V1 (#4086)

Browse Source 
Drop VLLM_USE_V1 usage.  This env has been removed from vLLM already.

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-11-11 15:43:39 +08:00
committed by GitHub
parent d5567680a2
commit f811a24bf0
21 changed files with 7 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/e2e/nightly/features/test_prefix_cache_deepseek_r1_0528_w8a8.py
View File

@@ -72,7 +72,6 @@ async def test_models(model: str) -> None:
"OMP_PROC_BIND": "false",
"HCCL_BUFFSIZE": "1024",
"PYTORCH_NPU_ALLOC_CONF": "expandable_segments:True",
"VLLM_USE_V1": "1"
}
additional_config = {
"ascend_scheduler_config": {

1
tests/e2e/nightly/models/test_qwq_32b.py
View File

@@ -73,7 +73,6 @@ async def test_models(model: str, mode: str, tp_size: int) -> None:
env_dict = {
"TASK_QUEUE_ENABLE": "1",
"OMP_PROC_BIND": "false",
"VLLM_USE_V1": "1",
"HCCL_OP_EXPANSION_MODE": "AIV",
"VLLM_ASCEND_ENABLE_FLASHCOMM": "1",
"VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE": "1",