-
Notifications
You must be signed in to change notification settings - Fork 400
Pull requests: NovaSky-AI/SkyRL
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Preserve Tinker training updates across chunks and retries
#2008
opened Aug 10, 2026 by
yapdianang
•
Draft
perf(sample-support): reuse replay scores for entropy
#2004
opened Aug 7, 2026 by
dyurk-lila
Contributor
Loading…
Initialize base inference before training model creation
#2003
opened Aug 7, 2026 by
j316chuck
Contributor
Loading…
[tinker] Keep the multi-tenant LoRA runtime warm on last unload
#2001
opened Aug 7, 2026 by
avigyabb
Collaborator
Loading…
[fix][megatron] Make multi-LoRA adapter swaps safe against colocation offload
#2000
opened Aug 7, 2026 by
erictang000
Collaborator
Loading…
[fix][train] Shut down DataLoader workers on exit
#1998
opened Aug 6, 2026 by
bvolpato
Contributor
Loading…
Enable load_weights_only in checkpointing
#1996
opened Aug 6, 2026 by
j316chuck
Contributor
Loading…
fix(lora): backload optimizer before adapter swap
#1991
opened Aug 5, 2026 by
pcmoritz
Collaborator
Loading…
[deps] Upgrade vllm-router and fix 0.1.15 startup
#1988
opened Aug 5, 2026 by
bvolpato
Contributor
Loading…
test(tx): scale the MoE LoRA tolerance to the output magnitude
#1987
opened Aug 5, 2026 by
pranavraja99
Loading…
feat(generators): add generator.skip_failed_rollouts
#1986
opened Aug 5, 2026 by
pranavraja99
Loading…
fix(train): reject a train_batch_size that truncates the prompt batch to zero
#1985
opened Aug 5, 2026 by
pranavraja99
Loading…
[perf][tinker] Resolve awaited requests with one shared batched poller
#1978
opened Aug 4, 2026 by
avigyabb
Collaborator
Loading…
Previous Next
ProTip!
Add no:assignee to see everything that’s not assigned.