Skip to content

Pull requests: PrimeIntellect-ai/prime-rl

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

Log per-server inference metrics
#2650 opened May 27, 2026 by samsja Member Loading…
R3 delta replay picks (no configs)
#2648 opened May 27, 2026 by samsja Member Loading…
R3 delta replay picks
#2647 opened May 27, 2026 by samsja Member Draft
[codex] Offload orchestrator rollout postprocess
#2646 opened May 27, 2026 by samsja Member Draft
feat(sft): default loss_mask to renderer's sampled_mask
#2644 opened May 26, 2026 by hallerite Member Loading…
3 tasks done
exp: verifiers v1 smoke configs
#2637 opened May 26, 2026 by mikasenghaas Member Draft
Support delta-only routed experts replay
#2632 opened May 25, 2026 by S1ro1 Collaborator Draft
Feat/sft on tool outputs
#2625 opened May 25, 2026 by snimu Collaborator Draft
chore(configs): router replay perf repro
#2614 opened May 24, 2026 by mikasenghaas Member Draft
[codex] Add sparse filesystem weight broadcast
#2607 opened May 23, 2026 by samsja Member Draft
Add token export mask visualizer
#2606 opened May 23, 2026 by samsja Member Loading…
Use sampling chat template kwargs for renderer RL
#2605 opened May 23, 2026 by eligotts Contributor Draft
Train against raw policy logprobs
#2604 opened May 23, 2026 by samsja Member Draft
fix: keep sampling args per token
#2603 opened May 23, 2026 by samsja Member Draft
[DO NOT MERGE] NIXL Working state
#2598 opened May 22, 2026 by S1ro1 Collaborator Draft
Feat/r3 prod v2
#2593 opened May 22, 2026 by samsja Member Draft
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.