main

GGitHubfix(workflow): account for thinking prefill in Geometry3K rewards (#1708)

6f4feca3创建于 5 天前历史提交

文件	最后提交记录	最后更新时间
anthropic	chore: enforce license (#1171)	5 个月前
langchain	chore: enforce license (#1171)	5 个月前
openai	fix(workflow): account for thinking prefill in Geometry3K rewards (#1708) * fix(workflow): account for thinking prefill in Geometry3K rewards * fix(workflow): use explicit thinking prefill for Geometry3K rewards * fix(dataset): derive thinking prefill from chat template output * test: defer Geometry3K dataset prefill coverage * test: restore baseline Geometry3K agent coverage	5 天前
openai_agent	chore: enforce license (#1171)	5 个月前
__init__.py	chore: enforce license (#1171)	5 个月前
multi_turn.py	fix(ppo): track trajectory truncation explicitly (#1637) Dynamic padding width identifies the longest trajectory in a batch, not whether generation exhausted its token budget. Propagate the inference stop reason and use it consistently for reward masking, GAE bootstrapping, and truncation metrics. Select bootstrap values from each trajectory's final valid token for both token- and turn-level GAE, filter the metadata at model boundaries, and retain the legacy heuristic for custom workflows that do not provide it. Signed-off-by: Bo Yang <yb550079@antgroup.com>	24 天前
rlvr.py	fix(ppo): track trajectory truncation explicitly (#1637) Dynamic padding width identifies the longest trajectory in a batch, not whether generation exhausted its token budget. Propagate the inference stop reason and use it consistently for reward masking, GAE bootstrapping, and truncation metrics. Select bootstrap values from each trajectory's final valid token for both token- and turn-level GAE, filter the metadata at model boundaries, and retain the legacy heuristic for custom workflows that do not provide it. Signed-off-by: Bo Yang <yb550079@antgroup.com>	24 天前
vision_rlvr.py	perf: reduce duplicated VLM rollout processing and transfers (#1671) * perf(infra): add group-scoped processor cache * perf(workflow): reuse processor results across VLM rollout groups * perf(experimental): cache agent multimodal prompt processing * perf(experimental): share processor cache across proxy sessions * perf(experimental): add grouped multimodal tensor references * perf(experimental): share tensor references across proxy sessions * perf(infra): preserve shared RTensor aliases * perf(infra): preserve aliases across staged engine RPCs * perf(trainer): avoid multimodal advantage RPC transfers * test(experimental): complete multimodal export fixtures * fix(experimental): prevent shared tensor refs from surviving store reuse * fix(infra): cancel rollout siblings before group finalization * fix(infra): retain source tensors during alias-preserving remotize	16 天前