[refact] unified soc_version code (#4359)

### What this PR does / why we need it?

Currently, there are two paths to judge the chip type in code,
`get_ascend_soc_version` use `get_soc_version` api in torch_npu, and
`is_310p` `use _build_info.__soc_version__`, which generate when
install. We need to unify the two paths.

We need to unify these codes based on the following points:

1. We need to ensure consistency in chip type judgment between compiling
and running states;
2. In compiling state, we need chip type to complete op's compilation,
but in running state, we only need device
type(910B/910_93/310P/910_95/etc) to make code branch judgement;
3. In compiling state, torch_npu may not have been installed yet, so we
can't use torch_npu's api.

Based on the above points, we have made the following changes:

1. When user set env `SOC_VERSION`, use it; when not set, query
soc_version by `npu-smi`;
2. generate device_type based on soc_version when compiling, and write
`__device_type__` instead of `__soc_version__` in `_build_info.py`;
3. In running state, use `__device_type__` to judge code branch.

### Does this PR introduce _any_ user-facing change?

When not set env `SOC_VERSION`, it will not be `ASCEND910B1` by default,
we will query soc_version by `npu-smi`. And env `SOC_VERSION` must be in
the list `soc_to_device` in `setup.py`.

- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

Signed-off-by: zzzzwwjj <1183291235@qq.com>
This commit is contained in:
zzzzwwjj
2025-11-26 14:28:55 +08:00
committed by GitHub
parent a91e76cd84
commit 136ea9ff56
42 changed files with 361 additions and 243 deletions

View File

@@ -52,7 +52,7 @@ class TestNPUWorker(TestBase):
@patch("vllm_ascend.worker.worker_v1.register_ascend_customop")
@patch("vllm_ascend.worker.worker_v1.get_ascend_config")
@patch("vllm_ascend.worker.worker_v1.init_ascend_config")
@patch("vllm_ascend.worker.worker_v1.init_ascend_soc_version")
@patch("vllm_ascend.worker.worker_v1.check_ascend_device_type")
@patch("vllm_ascend.worker.worker_v1.try_register_lib")
@patch(init_cached_hf_modules_path)
@patch("vllm_ascend.worker.worker_v1.NPUWorker._init_profiler")
@@ -61,7 +61,7 @@ class TestNPUWorker(TestBase):
mock_init_profiler,
mock_init_cached_hf_modules,
mock_try_register_lib,
mock_init_ascend_soc_version,
mock_check_ascend_device_type,
mock_init_ascend_config,
mock_get_ascend_config,
mock_register_ascend_customop,
@@ -93,7 +93,7 @@ class TestNPUWorker(TestBase):
mock_register_atb_extensions.assert_called_once()
mock_register_ascend_customop.assert_called_once()
mock_init_ascend_config.assert_called_once_with(self.vllm_config_mock)
mock_init_ascend_soc_version.assert_called_once()
mock_check_ascend_device_type.assert_called_once()
# Verify try_register_lib call
mock_try_register_lib.assert_called_once_with(
@@ -114,7 +114,7 @@ class TestNPUWorker(TestBase):
@patch("vllm_ascend.worker.worker_v1.register_ascend_customop")
@patch("vllm_ascend.worker.worker_v1.get_ascend_config")
@patch("vllm_ascend.worker.worker_v1.init_ascend_config")
@patch("vllm_ascend.worker.worker_v1.init_ascend_soc_version")
@patch("vllm_ascend.worker.worker_v1.check_ascend_device_type")
@patch("vllm_ascend.worker.worker_v1.try_register_lib")
@patch(init_cached_hf_modules_path)
@patch("vllm_ascend.worker.worker_v1.NPUWorker._init_profiler")
@@ -123,7 +123,7 @@ class TestNPUWorker(TestBase):
mock_init_profiler,
mock_init_cached_hf_modules,
mock_try_register_lib,
mock_init_ascend_soc_version,
mock_check_ascend_device_type,
mock_init_ascend_config,
mock_get_ascend_config,
mock_register_ascend_customop,
@@ -159,7 +159,7 @@ class TestNPUWorker(TestBase):
@patch("vllm_ascend.worker.worker_v1.register_ascend_customop")
@patch("vllm_ascend.worker.worker_v1.get_ascend_config")
@patch("vllm_ascend.worker.worker_v1.init_ascend_config")
@patch("vllm_ascend.worker.worker_v1.init_ascend_soc_version")
@patch("vllm_ascend.worker.worker_v1.check_ascend_device_type")
@patch("vllm_ascend.worker.worker_v1.try_register_lib")
@patch(init_cached_hf_modules_path)
@patch("vllm_ascend.worker.worker_v1.NPUWorker._init_profiler")
@@ -168,7 +168,7 @@ class TestNPUWorker(TestBase):
mock_init_profiler,
mock_init_cached_hf_modules,
mock_try_register_lib,
mock_init_ascend_soc_version,
mock_check_ascend_device_type,
mock_init_ascend_config,
mock_get_ascend_config,
mock_register_ascend_customop,