[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:
RAM
2025-12-05 20:01:33 +08:00
committed by GitHub
parent 8545b705ed
commit 96d2d4877b
24 changed files with 592 additions and 24 deletions

View File

@@ -568,6 +568,7 @@ class LLMEngine:
f" --logprobs_mode {self.cfg.model_config.logprobs_mode}"
f" --max_logprobs {self.cfg.model_config.max_logprobs}"
f" --eplb_config '{self.cfg.eplb_config.to_json_string()}'"
f" --routing_replay_config '{self.cfg.routing_replay_config.to_json_string()}'"
)
if self.cfg.structured_outputs_config.logits_processors is not None:
arguments += f" --logits-processors {' '.join(self.cfg.structured_outputs_config.logits_processors)}"