Skip to content

Pull requests: PrimeIntellect-ai/prime-rl

New pull request New
90 Open 1,715 Closed
90 Open 1,715 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

feat: Vendor VeriHop env and add configs/verihop/rl.toml
#2068 opened Mar 21, 2026 by nevasini1 Loading…
3
feat: add multimodal SFT support
#2067 opened Mar 21, 2026 by hallerite Loading…
4 tasks done
4
feat: make vision encoder optionally trainable
#2066 opened Mar 21, 2026 by hallerite Loading…
4 tasks done
3
perf: run VLM image preprocessing in thread to unblock event loop
#2065 opened Mar 21, 2026 by hallerite Loading…
3 tasks done
fix: skip multimodal samples that exceed seq_len instead of truncating
#2064 opened Mar 21, 2026 by hallerite Loading…
5 tasks done
feat: add explicit vlm config flag for VLM detection
#2063 opened Mar 21, 2026 by hallerite Loading…
5 tasks done
5
chore: consolidate VLM detection in trainer
#2062 opened Mar 21, 2026 by hallerite Loading…
2 tasks done
validate VLM dtype in configs
#2060 opened Mar 21, 2026 by rasdani Loading…
3
chore: update dependency versions to match upstream
#2059 opened Mar 21, 2026 by S1ro1 Loading…
2 tasks
Fix In-Group Evals
#2057 opened Mar 20, 2026 by hubert-marek • Draft
selective ac
#2055 opened Mar 20, 2026 by faresobeid Loading…
13
add executor autoscaling
#2054 opened Mar 19, 2026 by mikasenghaas Loading…
2 tasks
3
SFT distillation: bug fixes, VLM support, and pretokenization optimization
#2053 opened Mar 19, 2026 by eligotts Loading…
6 tasks done
19
quick fix for sft on single run
#2052 opened Mar 19, 2026 by Jackmin801 • Draft
1
fix: wire default_chat_template_kwargs to chat handler and /tokenize
#2050 opened Mar 19, 2026 by mudithj Loading…
4 tasks done
add glm air config for 4 nodes training
#2047 opened Mar 19, 2026 by samsja Loading…
feat: add NemotronH (Nemotron-3-Super-120B-A12B) model support
#2046 opened Mar 19, 2026 by samsja Loading…
6 of 7 tasks
2
feat: skip master weight gathering flag
#2045 opened Mar 18, 2026 by S1ro1 Loading…
1
feat: collect and log per-engine inference server metrics to W&B
#2043 opened Mar 18, 2026 by mikasenghaas • Draft
2
Add token usage reporting for billing
#2042 opened Mar 18, 2026 by shayonj Loading…
1 task
6
vLLM monkey-patches for dcp support on tp > node gpu count
#2041 opened Mar 18, 2026 by JannikSt Loading…
20
fix: compute GR3 baseline from length-corrected rewards
#2040 opened Mar 18, 2026 by rasdani • Draft
feat: integrate FP8 weight transfer format
#2038 opened Mar 17, 2026 by S1ro1 Loading…
4
feat: add sample-level loss normalization for SFT
#2032 opened Mar 16, 2026 by hallerite Loading…
9 tasks done
7
Fix config validation, engine resume, and CHANGELOG
#2031 opened Mar 16, 2026 by cursor bot • Draft
ProTip! Follow long discussions with comments:>50.