[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

@@ -50,11 +50,11 @@ env_variables: Dict[str, Callable[[], Any]] = {
# value is None, which means the system default C compiler will be used.
"C_COMPILER":
lambda: os.getenv("C_COMPILER", None),
# The version of the Ascend chip. If not set, the default value is
# ASCEND910B1(Available for A2 and A3 series). It's used for package building.
# The version of the Ascend chip. It's used for package building.
# If not set, we will query chip info through `npu-smi`.
# Please make sure that the version is correct.
"SOC_VERSION":
lambda: os.getenv("SOC_VERSION", "ASCEND910B1"),
lambda: os.getenv("SOC_VERSION", None),
# If set, vllm-ascend will print verbose logs during compilation
"VERBOSE":
lambda: bool(int(os.getenv('VERBOSE', '0'))),