-
Notifications
You must be signed in to change notification settings - Fork 220
Pull requests: PrimeIntellect-ai/prime-rl
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Serialize VLM pixel_values as raw bytes for 8-10x faster preprocessing
#1923
opened Mar 2, 2026 by
cdreetz
Loading…
1 of 2 tasks
feat: add mini Qwen3-VL model for local e2e RL testing
#1919
opened Mar 1, 2026 by
samsja
Loading…
4 tasks done
fix: type-aware micro batch distribution to prevent FSDP hang with VLMs
#1918
opened Mar 1, 2026 by
samsja
Loading…
5 tasks done
Fix GLM4-MoE HF export and RL vLLM reload compatibility
#1886
opened Feb 25, 2026 by
mansimov
Loading…
Fix weight update race condition between trainer cleanup and orchestrator
#1857
opened Feb 23, 2026 by
cdreetz
Loading…
fix: cast Path to str when spawning tail subprocess
#1824
opened Feb 18, 2026 by
enlightened88
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-02-02.