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

[CI] Upgrade vllm to 0.9.1 (#1165)

Browse Source 
1. upgrade vllm to 0.9.1. 0.9.0 is not supported for main branch now.
keep doc to 0.9.0 until we release the first 0.9.1 release.
2. disable V0 test for PR
3. move actionlint check to lint job

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-06-11 16:33:11 +08:00
committed by GitHub
parent e46dc142bf
commit 4f5964420e
19 changed files with 72 additions and 320 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
tests/singlecard/compile/test_simple.py
View File

@@ -14,8 +14,6 @@ from vllm.config import (CompilationConfig, CompilationLevel, VllmConfig,
set_current_vllm_config)
from vllm.utils import direct_register_custom_op
from vllm_ascend.utils import vllm_version_is
global_counter = 0
# create a library to hold the custom op
@@ -93,28 +91,14 @@ def test_simple_piecewise_compile():
model = SillyModel(vllm_config=vllm_config, prefix="")
inputs = torch.randn(100).npu()
if vllm_version_is("0.9.0"):
kwargs = {
"num_graphs_seen": 1, # one graph for the model
"num_piecewise_graphs_seen": 5, # 2 * num_layers + 1
"num_piecewise_capturable_graphs_seen": 3, # 1 + num_layers
"num_backend_compilations":
3, # num_piecewise_capturable_graphs_seen
"num_cudagraph_caputured":
6 # num_cudagraph_sizes * num_piecewise_capturable_graphs_seen
}
else:
kwargs = {
"num_graphs_seen": 1, # one graph for the model
"num_piecewise_graphs_seen": 5, # 2 * num_layers + 1
"num_piecewise_capturable_graphs_seen": 3, # 1 + num_layers
"num_backend_compilations":
3, # num_piecewise_capturable_graphs_seen
"num_cudagraph_captured":
6 # num_cudagraph_sizes * num_piecewise_capturable_graphs_seen
}
kwargs = {
"num_graphs_seen": 1, # one graph for the model
"num_piecewise_graphs_seen": 5, # 2 * num_layers + 1
"num_piecewise_capturable_graphs_seen": 3, # 1 + num_layers
"num_backend_compilations": 3, # num_piecewise_capturable_graphs_seen
"num_cudagraph_captured":
6 # num_cudagraph_sizes * num_piecewise_capturable_graphs_seen
}
with compilation_counter.expect(kwargs):
model(inputs)