-
Notifications
You must be signed in to change notification settings - Fork 560
Pull requests: rllm-org/rllm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(trainer): add Fireworks backend
#579
opened May 13, 2026 by
kylemontgomery1
Collaborator
•
Draft
2 of 14 tasks
feat(eval): forward sampling params through
rllm eval into AgentFlowEngine
#578
opened May 12, 2026 by
listar2000
Collaborator
Loading…
2 tasks done
feat(examples): add AgentCore MigrationBench training example (verl + Qwen3-Coder-30B)
#577
opened May 12, 2026 by
luyuzhe111
Collaborator
•
Draft
refactor(unified_trainer): extract step merging into a shared backend-agnostic module
#576
opened May 10, 2026 by
listar2000
Collaborator
Loading…
2 tasks done
feat(train): unify train + eval on AgentFlowEngine for harbor/sandbox
#571
opened May 8, 2026 by
jeffreysijuntan
Contributor
Loading…
2 of 3 tasks
feat(verl): patch zmq IPC id to depend on job id (volcengine/verl#6246)
#569
opened May 7, 2026 by
listar2000
Collaborator
•
Draft
4 of 5 tasks
feat(console): operator UI mounted on the gateway; retire visualizer.py
#558
opened May 5, 2026 by
jeffreysijuntan
Contributor
Loading…
3 tasks done
feat(harnesses): opencode/mini-swe-agent/oracle + Harbor 0.5 + --runtime flag
#557
opened May 5, 2026 by
jeffreysijuntan
Contributor
Loading…
3 tasks done
feat(eval): drop LiteLLM, in-process gateway + tunnel + cleanup
#556
opened May 5, 2026 by
jeffreysijuntan
Contributor
Loading…
3 tasks done
refactor(engine): introduce FlowEngine base, rename WorkflowEngine
#555
opened May 5, 2026 by
listar2000
Collaborator
•
Draft
4 of 14 tasks
feat(model-gateway): upstream-proxy mode + run lifecycle
#553
opened May 5, 2026 by
jeffreysijuntan
Contributor
Loading…
2 tasks done
feat(model-gateway): X-RLLM-* headers + inbound bearer auth
#552
opened May 5, 2026 by
jeffreysijuntan
Contributor
Loading…
3 tasks done
feat(model-gateway): trace store schema v2
#551
opened May 5, 2026 by
jeffreysijuntan
Contributor
Loading…
2 of 3 tasks
feat(verl): fully-async separated mode for VerlBackend
#545
opened May 2, 2026 by
kylemontgomery1
Collaborator
Loading…
14 tasks
fix(verl): build transform attention masks from sequence lengths
#517
opened Apr 29, 2026 by
JasonWei05
Collaborator
Loading…
3 of 14 tasks
fix(verl): preserve multi-turn tool-call prefix extension for math tool agent for Qwen 3 models
#516
opened Apr 29, 2026 by
JasonWei05
Collaborator
•
Draft
6 of 14 tasks
fix: unified async trainer with verl backend
#493
opened Apr 6, 2026 by
yifannnwu
Contributor
Loading…
1 task done
refactor: replace bypass_render_with_parser with TinkerChatTemplateParser
#489
opened Apr 6, 2026 by
listar2000
Collaborator
•
Draft
2 of 3 tasks
Add strict DPO objective plumbing and preference-pair groundwork
#477
opened Apr 2, 2026 by
taivu1998
Contributor
Loading…
Add early-finalize continuation for truncated reasoning rollouts
#475
opened Apr 2, 2026 by
taivu1998
Contributor
Loading…
Added adapator layers for to-be-deprecated AgentWorkflowEngine and AgentExecutionEngine
#413
opened Mar 3, 2026 by
boredbichon67
Contributor
Loading…
feat: Add SkyRL backend for unified trainer
#407
opened Feb 28, 2026 by
jeewoo-lee
Contributor
Loading…
Add Strands SDK integration for RAG agent training
#359
opened Dec 31, 2025 by
JunjieAraoXiong
Loading…
Previous Next
ProTip!
Exclude everything labeled
bug with -label:bug.