Skip to content

Pull requests: allenai/open-instruct

New pull request New
24 Open 1,322 Closed
24 Open 1,322 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

Fix DataPreparationActor hanging on shutdown
#1611 opened Apr 14, 2026 by hamishivi Collaborator Loading…
3 tasks done
2
Dr tulu replication
#1609 opened Apr 14, 2026 by hamishivi Collaborator Loading…
10
Warn about checkpoint disk space only on the first checkpoint
#1608 opened Apr 13, 2026 by mnoukhov Contributor Loading…
4
Use Ray to validate that allocated gpus correspond to requeusted # of GPUs
#1606 opened Apr 13, 2026 by mnoukhov Contributor Loading…
15
Fix: deterministic downsampling
#1603 opened Apr 11, 2026 by mnoukhov Contributor Loading…
9
Auto-update CHANGELOG.md from PR descriptions on merge
#1596 opened Apr 9, 2026 by finbarrtimbers Collaborator Loading…
2 of 3 tasks
6
Stabilize GRPO LLM judge calls by routing them through the guarded LiteLLM helper
#1587 opened Apr 3, 2026 by taivu1998 Loading…
3
grpo_fast: harden single-node startup resource checks and diagnostics
#1586 opened Apr 3, 2026 by taivu1998 Loading…
6
Changes DataPreparationActor so that we can configure it into a replay buffer
#1583 opened Apr 2, 2026 by finbarrtimbers Collaborator Loading…
8
Add OLMo-core SFT implementation
#1579 opened Mar 31, 2026 by finbarrtimbers Collaborator Loading…
10
Fix GRPO rank_microbatch_size units
#1557 opened Mar 24, 2026 by finbarrtimbers Collaborator Loading…
1 task
4
WIP
#1555 opened Mar 24, 2026 by mnoukhov Contributor • Draft
7
Priority local eval queue for grpo_fast
#1553 opened Mar 23, 2026 by mnoukhov Contributor Loading…
24
2GPU Olmo-core GRPO
#1551 opened Mar 23, 2026 by mnoukhov Contributor • Draft
4
DELTA benchmark
#1541 opened Mar 19, 2026 by mnoukhov Contributor • Draft
6
Rename num_unique_prompts_rollout and num_samples_per_prompt_rollout
#1538 opened Mar 19, 2026 by finbarrtimbers Collaborator Loading…
3
Migrate to vLLM native weight transfer API
#1515 opened Mar 6, 2026 by finbarrtimbers Collaborator Loading…
15
Port vLLM v1 AsyncMPClient weight-update flow
#1506 opened Mar 2, 2026 by mnoukhov Contributor Loading…
3
Remove cast from vLLM tool definitions typing
#1504 opened Mar 2, 2026 by finbarrtimbers Collaborator Loading…
3
Rename TIS ratio cap, add low bound and hard filter flag
#1503 opened Mar 2, 2026 by finbarrtimbers Collaborator Loading…
8
Add SWERLSandboxEnv for per-sample Docker tasks with submit-based evaluation
#1492 opened Feb 24, 2026 by hamishivi Collaborator • Draft
4 tasks done
13
Require checkpoint on Beaker restarts for DPO and GRPO training codex
#1469 opened Feb 10, 2026 by finbarrtimbers Collaborator Loading…
5
WIP: Add PPO with value model support to grpo_fast.py
#1462 opened Feb 4, 2026 by hamishivi Collaborator • Draft
1 of 6 tasks
6
Adds Olmo-core SFT script that matches finetune.py's interface and Olmo-core's efficiency
#1327 opened Jan 7, 2026 by finbarrtimbers Collaborator Loading…
2 of 3 tasks
9
ProTip! Updated in the last three days: updated:>2026-04-11.