mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
[Optimize] Support and robust for tpN for PD (#4595)
* [Optimize] Support and robust for tpN for PD * fix * fix * support dpM tpN for cache messager * fix * fix token counter * fix bug for merge develop * fix bug * robust cache messager for v0
This commit is contained in:
@@ -275,6 +275,7 @@ class SplitwiseConnector:
|
||||
decode_diagg = task.disaggregate_info["cache_info"]
|
||||
task.disaggregate_info["cache_info"] = self.cfg.disaggregate_info["cache_info"]
|
||||
task.disaggregate_info["cache_info"]["rdma"]["current_id"] = current_id
|
||||
task.disaggregate_info["role"] = "decode"
|
||||
self._send_message(addr, "prefill", [task])
|
||||
task.disaggregate_info["cache_info"] = decode_diagg
|
||||
task.disaggregate_info["role"] = "prefill"
|
||||
|
||||
Reference in New Issue
Block a user