-
Notifications
You must be signed in to change notification settings - Fork 0
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
Add First Agentic Rollout guide
area/agenticIssues or PRs related to agentic RL, agent functions, and trajectoriesIssues or PRs related to agentic RL, agent functions, and trajectoriesarea/dxIssues or PRs related to developer experience (error messages, ergonomics, onboarding)Issues or PRs related to developer experience (error messages, ergonomics, onboarding)kind/documentationCategorizes issue or PR as related to documentationCategorizes issue or PR as related to documentationStatus: Open.Add Core Concepts runtime mental model
area/dxIssues or PRs related to developer experience (error messages, ergonomics, onboarding)Issues or PRs related to developer experience (error messages, ergonomics, onboarding)kind/documentationCategorizes issue or PR as related to documentationCategorizes issue or PR as related to documentationStatus: Open.Add Troubleshooting hub docs
area/dxIssues or PRs related to developer experience (error messages, ergonomics, onboarding)Issues or PRs related to developer experience (error messages, ergonomics, onboarding)kind/documentationCategorizes issue or PR as related to documentationCategorizes issue or PR as related to documentationpriority/important-soonMust be staffed and worked on either currently, or very soonMust be staffed and worked on either currently, or very soonStatus: Open.Add Example Gallery docs
area/dxIssues or PRs related to developer experience (error messages, ergonomics, onboarding)Issues or PRs related to developer experience (error messages, ergonomics, onboarding)kind/documentationCategorizes issue or PR as related to documentationCategorizes issue or PR as related to documentationStatus: Open.Add First Training and RLVR quickstarts
area/dxIssues or PRs related to developer experience (error messages, ergonomics, onboarding)Issues or PRs related to developer experience (error messages, ergonomics, onboarding)kind/documentationCategorizes issue or PR as related to documentationCategorizes issue or PR as related to documentationpriority/important-soonMust be staffed and worked on either currently, or very soonMust be staffed and worked on either currently, or very soonStatus: Open.Add Overview and Choose Your Path docs
area/dxIssues or PRs related to developer experience (error messages, ergonomics, onboarding)Issues or PRs related to developer experience (error messages, ergonomics, onboarding)kind/documentationCategorizes issue or PR as related to documentationCategorizes issue or PR as related to documentationpriority/important-soonMust be staffed and worked on either currently, or very soonMust be staffed and worked on either currently, or very soonStatus: Open.Write AReno recipe system design
area/algorithmsIssues or PRs related to training algorithms (SFT, DPO, GSPO, GRPO, PPO)Issues or PRs related to training algorithms (SFT, DPO, GSPO, GRPO, PPO)area/cliIssues or PRs related to the CLI (areno train, areno serve)Issues or PRs related to the CLI (areno train, areno serve)area/dxIssues or PRs related to developer experience (error messages, ergonomics, onboarding)Issues or PRs related to developer experience (error messages, ergonomics, onboarding)kind/designCategorizes issue or PR as related to design discussionCategorizes issue or PR as related to design discussionpriority/important-soonMust be staffed and worked on either currently, or very soonMust be staffed and worked on either currently, or very soonStatus: Open.#96 In inclusionAI/AReno;Add GPU-guarded numerical equivalence tests for native attention kernels
area/accelIssues or PRs related to CUDA kernels and fused operatorsIssues or PRs related to CUDA kernels and fused operatorsarea/testingIssues or PRs related to the test suite and test infrastructureIssues or PRs related to the test suite and test infrastructurekind/featureCategorizes issue or PR as related to a new featureCategorizes issue or PR as related to a new featureStatus: Open.#81 In inclusionAI/AReno;Fix native attention design-claim mismatch: dense kernel and custom backwards unused
area/accelIssues or PRs related to CUDA kernels and fused operatorsIssues or PRs related to CUDA kernels and fused operatorskind/cleanupCategorizes issue or PR as related to cleaning up code, process, or technical debtCategorizes issue or PR as related to cleaning up code, process, or technical debtStatus: Open.#80 In inclusionAI/AReno;Decide whether GRPO/GSPO need real old-logprob ratios
area/algorithmsIssues or PRs related to training algorithms (SFT, DPO, GSPO, GRPO, PPO)Issues or PRs related to training algorithms (SFT, DPO, GSPO, GRPO, PPO)area/apiIssues or PRs related to the SDK/Trainer public APIIssues or PRs related to the SDK/Trainer public APIkind/designCategorizes issue or PR as related to design discussionCategorizes issue or PR as related to design discussionStatus: Open.#68 In inclusionAI/AReno;Document current GSPO surrogate ratio semantics
area/algorithmsIssues or PRs related to training algorithms (SFT, DPO, GSPO, GRPO, PPO)Issues or PRs related to training algorithms (SFT, DPO, GSPO, GRPO, PPO)area/testingIssues or PRs related to the test suite and test infrastructureIssues or PRs related to the test suite and test infrastructurekind/cleanupCategorizes issue or PR as related to cleaning up code, process, or technical debtCategorizes issue or PR as related to cleaning up code, process, or technical debtStatus: Open.#67 In inclusionAI/AReno;Document current GRPO surrogate ratio semantics
area/algorithmsIssues or PRs related to training algorithms (SFT, DPO, GSPO, GRPO, PPO)Issues or PRs related to training algorithms (SFT, DPO, GSPO, GRPO, PPO)area/testingIssues or PRs related to the test suite and test infrastructureIssues or PRs related to the test suite and test infrastructurekind/cleanupCategorizes issue or PR as related to cleaning up code, process, or technical debtCategorizes issue or PR as related to cleaning up code, process, or technical debtStatus: Open.#66 In inclusionAI/AReno;