[Refactor] Cleanup platform (#5566)
### What this PR does / why we need it?
1. add `COMPILATION_PASS_KEY` constant
2. clean up useless platform interface `empty_cache`, `synchronize`,
`mem_get_info`, `clear_npu_memory`
3. rename `CUSTOM_OP_REGISTERED` to `_CUSTOM_OP_REGISTERED`
4. remove uesless env `VLLM_ENABLE_CUDAGRAPH_GC`
NPUPlatform is the interface called by vLLM. Do not call it inner
vllm-ascend.
### Does this PR introduce _any_ user-facing change?
This PR is just a cleanup. All CI should pass.
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
7157596103
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
@@ -28,6 +28,7 @@ from torch.fx import GraphModule
|
||||
from vllm.compilation.compiler_interface import CompilerInterface
|
||||
|
||||
from vllm_ascend.ascend_config import get_ascend_config
|
||||
from vllm_ascend.utils import COMPILATION_PASS_KEY
|
||||
|
||||
|
||||
def compile_fx(graph: GraphModule, example_inputs: list,
|
||||
@@ -51,7 +52,7 @@ def fusion_pass_compile(
|
||||
) -> tuple[Optional[Callable], Optional[Any]]:
|
||||
|
||||
def compile_inner(graph, example_inputs):
|
||||
current_pass_manager = compiler_config["graph_fusion_manager"]
|
||||
current_pass_manager = compiler_config[COMPILATION_PASS_KEY]
|
||||
graph = current_pass_manager(graph, runtime_shape)
|
||||
return graph
|
||||
|
||||
|
||||
Reference in New Issue
Block a user