[Core] Make V1 work and enable V1 engine test (#389)

1. Make sure the version is string before parse in collect_env
2. Add basic V1 engine test

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-03-28 19:34:23 +08:00
committed by GitHub
parent 57a84bb7be
commit 31f29b9f30
8 changed files with 66 additions and 95 deletions

View File

@@ -210,7 +210,7 @@ class NPUWorker(WorkerBase):
def get_model(self) -> nn.Module:
return self.model_runner.get_model()
def get_kv_cache_spec(self) -> KVCacheSpec:
def get_kv_cache_spec(self) -> dict[str, KVCacheSpec]:
return self.model_runner.get_kv_cache_spec()
def initialize_from_config(self, kv_cache_config: KVCacheConfig) -> None: