mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
[RL] Support Rollout Routing Replay (#5321)
* [RL] Support Rollout Routing Replay * add routing indices cache * fix config bug and moe forward bug * R3 Support GLM * support eb4.5 * fix merge bug * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * add routing replay ci * support glm topk * support orther top_k * fix ci bug * pre-commit * only support chatcmpl --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yuanle Liu <yuanlehome@163.com>
This commit is contained in:
@@ -65,6 +65,7 @@ class RolloutModelConfig:
|
||||
data_parallel_size: int = 1,
|
||||
num_nextn_predict_layers: int = 0,
|
||||
eplb_config: str = {},
|
||||
routing_replay_config: str = None,
|
||||
):
|
||||
# Required parameters
|
||||
self.model = model_name_or_path
|
||||
@@ -113,6 +114,7 @@ class RolloutModelConfig:
|
||||
self.plas_attention_config = plas_attention_config
|
||||
self.num_nextn_predict_layers = num_nextn_predict_layers
|
||||
self.eplb_config = eplb_config
|
||||
self.routing_replay_config = routing_replay_config
|
||||
|
||||
def __str__(self):
|
||||
return "\n".join(f"{k}: {v}" for k, v in self.__dict__.items())
|
||||
|
||||
Reference in New Issue
Block a user