| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
chore: enforce license (#1171) | 6 个月前 | |
chore: migrate repo references from InclusionAI to areal-project (#1325) Update all internal URLs and org references after migrating the repository from InclusionAI/AReaL to areal-project/AReaL. Key changes: - Update GitHub repo URLs (github.com/inclusionAI/AReaL -> areal-project/AReaL) - Update GitHub Pages docs URLs (inclusionai.github.io -> areal-project.github.io) - Update GHCR Docker image refs (ghcr.io/inclusionai/ -> areal-project/) - Update CI workflow usernames and GitHub API org references - Update DeepWiki and gitcgr badge URLs - Update issue references in code comments HuggingFace model/dataset URLs intentionally left unchanged. Vendored directories (sglang-src, Megatron-LM, Megatron-Bridge) skipped. | 5 个月前 | |
fix(api): make vLLM prefix caching configuration explicit | 1 个月前 | |
feat(distillation): mopd implementation; aime, leetcode, and mopd dataset with examples | 2 个月前 | |
feat(vllm): unify rollouts on /inference/v1/generate Use one token-in/token-out transport for text and multimodal rollouts. Keep one collapsed marker per media item and let vLLM render raw media into its final EngineInput. Key changes: - Backport content_parts support to vLLM 0.23 - Carry expanded and collapsed prompt representations in lockstep - Route direct and DataProxy vLLM adapters through the stock endpoint - Preserve concat prompts across generation retries | 1 个月前 | |
fix(api): return float zero after async reward timeout (#1541) (#1651) AsyncRewardWrapper returned an integer zero when reward computation timed out, despite declaring a float result. The v1 OpenAI proxy only accepts dictionary or float rewards, so the fallback could raise ValueError instead of recording a zero reward. Return 0.0 from both wrapper-owned fallback paths and strengthen the existing timeout tests to verify the result type. Signed-off-by: Bo Yang <yb550079@antgroup.com> Co-authored-by: Bo Yang <83399667+harooos@users.noreply.github.com> | 1 个月前 | |
refactor(infra): change fork_workers API to use Job | 3 个月前 | |
chore: enforce license (#1171) | 6 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 6 个月前 | ||
| 5 个月前 | ||
| 1 个月前 | ||
| 2 个月前 | ||
| 1 个月前 | ||
| 1 个月前 | ||
| 3 个月前 | ||
| 6 个月前 |