[core]vllm-ascend support msMonitor tool (#3123)
### What this PR does / why we need it?
vllm-ascend support [msMonitor
](https://gitcode.com/Ascend/mstt/tree/master/msmonitor)tool to collect
performance of vllm-ascend
### Does this PR introduce _any_ user-facing change?
1.add env MSMONITOR_USE_DAEMON;
2.user cann enable msMonitor tool by setting MSMONITOR_USE_DAEMON=1
before run vllm-ascend model;
3.MSMONITOR_USE_DAEMON and VLLM_TORCH_PROFILER_DIR cannot both set
### How was this patch tested?
1.run vllm-ascend model while not set MSMONITOR_USE_DAEMON=1 or set
MSMONITOR_USE_DAEMON=0, model will run successfully;
2.run vllm-ascend model while set MSMONITOR_USE_DAEMON=1, run msMonitor
tool to collect profile data;
3.run vllm-ascend model while set MSMONITOR_USE_DAEMON=1 and
VLLM_TORCH_PROFILER_DIR, will raise error
- vLLM version: v0.10.2
- vLLM main:
f225ea7dd9
Signed-off-by: mei-feiyao <1332490378@qq.com>
This commit is contained in:
@@ -355,6 +355,28 @@ class TestNPUWorker(TestBase):
|
||||
|
||||
self.assertIn("Profiler is not enabled", str(cm.exception))
|
||||
|
||||
@patch("vllm_ascend.worker.worker_v1.envs_vllm")
|
||||
@patch("vllm_ascend.worker.worker_v1.envs_ascend")
|
||||
def test_profile_and_msmonitor_both_enabled_raises_error(
|
||||
self, mock_envs_vllm, mock_envs_ascend):
|
||||
"""Test profile method raises exception when both profiler and msmonitor are enabled"""
|
||||
from vllm_ascend.worker.worker_v1 import NPUWorker
|
||||
|
||||
mock_envs_vllm.VLLM_TORCH_PROFILER_DIR = "/path/to/traces"
|
||||
mock_envs_ascend.MSMONITOR_USE_DAEMON = 1
|
||||
|
||||
# Create worker mock
|
||||
with patch.object(NPUWorker, "__init__", lambda x, **kwargs: None):
|
||||
worker = NPUWorker()
|
||||
|
||||
# Test should raise exception
|
||||
with self.assertRaises(RuntimeError) as cm:
|
||||
_ = worker._init_profiler()
|
||||
|
||||
self.assertIn(
|
||||
"MSMONITOR_USE_DAEMON and VLLM_TORCH_PROFILER_DIR cannot be both set at the same time.",
|
||||
str(cm.exception))
|
||||
|
||||
def test_lora_methods(self):
|
||||
"""Test LoRA related methods"""
|
||||
from vllm_ascend.worker.worker_v1 import NPUWorker
|
||||
|
||||
Reference in New Issue
Block a user