Remove VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE (#5272)

`VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE` is only used together with
`VLLM_ASCEND_ENABLE_PREFETCH_MLP` which is useless totally. This PR
remove it.
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-12-25 11:09:56 +08:00
committed by GitHub
parent 13cd6362c6
commit 2ae0bad96d
8 changed files with 7 additions and 21 deletions

View File

@@ -108,11 +108,6 @@ env_variables: Dict[str, Callable[[], Any]] = {
"VLLM_ASCEND_MLP_DOWN_PREFETCH_SIZE":
lambda: int(
os.getenv("VLLM_ASCEND_MLP_DOWN_PREFETCH_SIZE", 18 * 1024 * 1024)),
# Whether to enable dense model and general optimizations for better performance.
# Since we modified the base parent class `linear`, this optimization is also applicable to other model types.
# However, there might be hidden issues, and it is currently recommended to prioritize its use with dense models.
"VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE":
lambda: bool(int(os.getenv("VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE", '0'))),
# Whether to enable msMonitor tool to monitor the performance of vllm-ascend.
"MSMONITOR_USE_DAEMON":
lambda: bool(int(os.getenv("MSMONITOR_USE_DAEMON", '0'))),