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

support torchair mode (#2641)

Browse Source 
### What this PR does / why we need it?
support torchair mode
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?

- vLLM version: v0.10.1.1
- vLLM main:
5438967fbc

Signed-off-by: zhangdepeng <zhangdepeng2@huawei.com>
Signed-off-by: p00465316 <panchao13@huawei.com>
Co-authored-by: zhangdepeng <zhangdepeng2@huawei.com>
This commit is contained in:
panchao-hub
2025-09-01 15:49:07 +08:00
committed by GitHub
parent b72e34013f
commit ea53f9076e
4 changed files with 19 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/torchair/torchair_model_runner.py
View File

@@ -324,6 +324,8 @@ class NPUTorchairModelRunner(NPUModelRunner):
communication_adaptation_310p()
config = torchair.CompilerConfig()
if get_ascend_config().torchair_graph_config.mode:
config.mode = get_ascend_config().torchair_graph_config.mode
config.experimental_config.frozen_parameter = True
# enabling tiling_schedule_optimize on 300I Duo has some bugs, so we have to
# disable it on 300I Duo platform now.