Skip to content

Pull requests: allenai/open-instruct

New pull request New
62 Open 1,203 Closed
62 Open 1,203 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Offline Distillation via DistillKit (Part One - Compression Helpers for Logit Capture)
#1525 opened Mar 12, 2026 by wolfecameron Loading…
36
Fix GRPO data prep actor checkpoint resume
#1523 opened Mar 11, 2026 by MohdElgaar Loading…
3
Add DeepSpeed universal checkpoint (UCP) support for GRPO
#1517 opened Mar 7, 2026 by MohdElgaar Loading…
5
Migrate to vLLM 0.16.0 native weight transfer API
#1515 opened Mar 6, 2026 by finbarrtimbers Loading…
9
Add SLR-Bench (Scalable Logical Reasoning) verifier and dataset support for RLVR
#1511 opened Mar 6, 2026 by lukashelff Loading…
5
Add model step logging for GRPO/vLLM
#1508 opened Mar 3, 2026 by mnoukhov Loading…
4
new vllm and transformers 5.2.0
#1507 opened Mar 2, 2026 by mnoukhov • Draft
4
Port vLLM v1 AsyncMPClient weight-update flow
#1506 opened Mar 2, 2026 by mnoukhov Loading…
3
Remove cast from vLLM tool definitions typing
#1504 opened Mar 2, 2026 by finbarrtimbers Loading…
3
Rename TIS ratio cap, add low bound and hard filter flag
#1503 opened Mar 2, 2026 by finbarrtimbers Loading…
7
Add AppWorld environment integration for GRPO
#1501 opened Feb 27, 2026 by hamishivi Loading…
3 tasks done
6
Fix dataset cache hashing for chat template changes
#1497 opened Feb 26, 2026 by mnoukhov Loading…
4
Fix dataset mixer split validation in combined datasets
#1494 opened Feb 24, 2026 by MohdElgaar Loading…
3
Add SWERLSandboxEnv for per-sample Docker tasks with submit-based evaluation
#1492 opened Feb 24, 2026 by hamishivi Loading…
4 tasks done
13
Remove vllm_num_engines from VLLMConfig; compute inline from cluster resources
#1482 opened Feb 19, 2026 by finbarrtimbers Loading…
9
Require checkpoint on Beaker restarts for DPO and GRPO training codex
#1469 opened Feb 10, 2026 by finbarrtimbers Loading…
5
Pass@K for local eval
#1464 opened Feb 6, 2026 by mnoukhov • Draft
6
WIP: Add PPO with value model support to grpo_fast.py
#1462 opened Feb 4, 2026 by hamishivi • Draft
1 of 6 tasks
6
Tillicum slurm launcher
#1450 opened Jan 31, 2026 by hamishivi • Draft
9
Avoid sync CUDA transfer in data loader codex
#1443 opened Jan 30, 2026 by finbarrtimbers Loading…
4
Add DPO OLMo-core support with MFU improvements
#1440 opened Jan 30, 2026 by finbarrtimbers Loading…
3 tasks
9
Fixes SFT checkpointing
#1435 opened Jan 28, 2026 by finbarrtimbers Loading…
7
Significantly improves dpo.py performance: ~40% MFU
#1430 opened Jan 27, 2026 by finbarrtimbers • Draft
3
Runs the benchmarks with the hybrid model
#1425 opened Jan 26, 2026 by finbarrtimbers Loading…
15
Add tool docs
#1410 opened Jan 21, 2026 by hamishivi Loading…
10
ProTip! Follow long discussions with comments:>50.