Support DP MLA (#1970)

This commit is contained in:
Ke Bao
2024-11-16 17:01:43 +08:00
committed by GitHub
parent 2f2e07439c
commit 976bc302e5
12 changed files with 395 additions and 63 deletions

View File

@@ -88,6 +88,9 @@ class TpModelWorkerClient:
def get_tp_cpu_group(self):
return self.worker.get_tp_cpu_group()
def get_tp_device_group(self):
return self.worker.get_tp_device_group()
def get_memory_pool(self):
return (
self.worker.model_runner.req_to_token_pool,