OpenRLHF
https://github.com/OpenRLHF/OpenRLHF
Distributed RLHF training framework built on Ray + DeepSpeed + vLLM — supports PPO/DPO/REINFORCE++/GRPO. Targeted at 70B+ models with efficient sample throughput.
Active · Verified 2026-10-27 · fresh as of 2026-10-27 · 17 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Distributed RLHF training framework repo fix
- Tier
- T2
- Section
- Training infrastructure
- Latest release
- v0.11.2 (2026-09-14) — openrlhf registry fix
- License
- Apache-2.0 repo fix
- Pricing
- searched not found fix
- Funding
- searched not found fix
- Freshness
- 2026-10-27 fix
- Layer
- model-infra repo fix
- Licensing
- open-source repo fix
- Developer activity
- OpenRank 3.53 (12-mo avg 8.14) · 24 participants — 2026-09 third-party fix
When to use
Optimised for: searched not found
Anti-fit: searched not found
Pros & cons
Pros
searched not found
Cons
searched not found
Claims & capabilities
Multi-node RLHF at 70B+ scale; vLLM-accelerated rollout.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Self-hosted only — library
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other training infrastructure in the catalog, ranked by inbound references.
- MLflow T1
Databricks-incubated open platform for ML lifecycle — tracking, projects, models, model registry. Standard ML-ops baseline. MLflow 3.0 (2024) added LLM-eval features.
- AWS SageMaker T1
AWS's managed ML platform — Studio, Training, HyperPod (large-scale clusters), Endpoints. Industry-standard for enterprise AWS-hosted training.
- Weights & Biases T1
Experiment-tracking and ML-ops platform (metrics, artifacts, sweeps, Weave tracing/evals). Acquired by CoreWeave (completed 2025-05-05, ~$1.7B); now part of CoreWeave Forge.
- Comet ML T2
ML experiment tracking + LLM evaluation platform (Opik for LLM eval). Comet competes head-to-head with Weights & Biases.
- Azure Machine Learning T1
Microsoft Azure's managed ML platform — pipelines, AutoML, Designer, prompt flow (LLM). Heavy integration with Azure OpenAI and Azure AI Studio.
- LoRA T3
Microsoft Research's Low-Rank Adapters method — trains rank-r matrices added to attention weights; 10000x parameter reduction. Foundation of all adapter-style fine-tuning.
Sources (16 cited facts, 1 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Distributed RLHF training framework repo
- What it does & what's distinct Distributed RLHF training framework built on Ray + DeepSpeed + vLLM — supports PPO/DPO/R… repo
- Claims / benefits Multi-node RLHF at 70B+ scale; vLLM-accelerated rollout. repo
- Created 2023 repo
- Latest release v0.11.2 (2026-09-14) — openrlhf registry
- License Apache-2.0 repo
- GitHub OpenRLHF/OpenRLHF — ~10.1k stars, last commit 2026-10 repo
- Deployment Self-hosted only — library repo
- Code/weights release Active — last commit 2026-05 · 9,490★ repo
- commit-trajectory [{"ym":"2024-04","cum":562},{"ym":"2024-05","cum":593},{"ym":"2024-06","cum":689},{"ym":… repo
- download-trajectory [{"ym":"2025-11","monthly":1215,"cum":1215},{"ym":"2025-12","monthly":2117,"cum":3332},{… registry
- architecture-deployment-locus local repo
- licensing-bucket open-source repo
- positioning-platform-vs-product platform repo
- taxonomy-three-layer-rollup model-infra repo
- developer-activity-opendigger {"activity":58.46,"as_of":"2026-09","openrank_12mo":8.14,"openrank_current":3.53,"partic… third-party
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)