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

Drop torchair (#4814)

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm_ascend/quantization/w8a8_dynamic.py
View File

@@ -111,10 +111,9 @@ class AscendW8A8DynamicFusedMoEMethod:
vllm_config = get_current_vllm_config()
ascend_config = get_ascend_config()
self.use_aclgraph = (
vllm_config.compilation_config.mode == CompilationMode.VLLM_COMPILE
and not vllm_config.model_config.enforce_eager
and not ascend_config.torchair_graph_config.enabled)
self.use_aclgraph = (vllm_config.compilation_config.mode
== CompilationMode.VLLM_COMPILE
and not vllm_config.model_config.enforce_eager)
self.dynamic_eplb = ascend_config.dynamic_eplb or ascend_config.expert_map_record_path
self.in_dtype = vllm_config.model_config.dtype