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

implement model runner v2 basic framework (#5051)

Browse Source 
### What this PR does / why we need it?
This PR aim to implement model runner v2 basic framework in vllm-ascend,
the e2e function is not guaranteed by this pr.
 
### Does this PR introduce _any_ user-facing change?
use envs.VLLM_USE_V2_MODEL_RUNNER to decide if choose model_runenr_v2.

### How was this patch tested?

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

---------

Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
This commit is contained in:
Ronald
2025-12-18 15:51:54 +08:00
committed by GitHub
parent 1c8c23de58
commit b69b04d3a9
16 changed files with 843 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/ut/test_platform.py
View File

@@ -445,7 +445,7 @@ class TestNPUPlatform(TestBase):
self.assertEqual(
vllm_config.parallel_config.worker_cls,
"vllm_ascend.worker.worker_v1.NPUWorker",
"vllm_ascend.worker.worker.NPUWorker",
)
test_ascend_config = TestNPUPlatform.mock_vllm_ascend_config()