[aclgraph] implentment NPUPiecewiseBackend to enable aclgraph (#836)
### What this PR does / why we need it? 1. Implentment `NPUPiecewiseBackend` to enable aclgraph 2. Eable aclgraph by default in V1, but raise error when running deepseek and raise warning when running models except for qwen ### How was this patch tested? CI pass with the new ut --------- Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
@@ -77,7 +77,7 @@ class VllmRunner:
|
||||
block_size: int = 16,
|
||||
enable_chunked_prefill: bool = False,
|
||||
swap_space: int = 4,
|
||||
enforce_eager: Optional[bool] = False,
|
||||
enforce_eager: Optional[bool] = True,
|
||||
**kwargs,
|
||||
) -> None:
|
||||
self.model = LLM(
|
||||
|
||||
Reference in New Issue
Block a user