Search results

Loss calculation of <code>GKDTrainer</code> may be inaccurate when performing gradient accumulation?

🏋 GKDRelated to GKDRelated to GKD

🐛 bugSomething isn't workingSomething isn't working

Status: Open.

#4719 In huggingface/trl;

· jue-jue-zi opened on Dec 18, 2025

Add RLVR (Reinforcement Learning with Verifiable Rewards) Trainer

✨ enhancementNew feature or requestNew feature or request

🏋 RewardRelated to Reward modellingRelated to Reward modelling

🏋 RLOORelated to RLOORelated to RLOO

Status: Open.

#4711 In huggingface/trl;

· mmjerge opened on Dec 17, 2025

qwen3_schema fails to parse multiple parallel tool calls

🐛 bugSomething isn't workingSomething isn't working

Status: Open.

#4708 In huggingface/trl;

· austinmw opened on Dec 17, 2025

GRPOTrainer: Relative LLM-as-a-judge rankings

✨ enhancementNew feature or requestNew feature or request

🏋 GRPORelated to GRPORelated to GRPO

Status: Open.

#4707 In huggingface/trl;

· austinmw opened on Dec 16, 2025

feat GRPOTrainer: Off-policy sequence masking from DeepSeek V3.2

✨ enhancementNew feature or requestNew feature or request

🏋 GRPORelated to GRPORelated to GRPO

Status: Open.

#4697 In huggingface/trl;

· casinca opened on Dec 15, 2025

LLVM error during GRPO training with Apple M4 Max

🏋 GRPORelated to GRPORelated to GRPO

🐛 bugSomething isn't workingSomething isn't working

Status: Open.

#4692 In huggingface/trl;

· neslihaneti opened on Dec 14, 2025

[SFT] High vRAM consumption during eval loop

⚡ PEFTRelated to PEFTRelated to PEFT

🏋 SFTRelated to SFTRelated to SFT

🐛 bugSomething isn't workingSomething isn't working

Status: Open.

#4679 In huggingface/trl;

· Khreas opened on Dec 11, 2025

[GRPO] evaluation at start fails, due to missing current_gradient_accumulation_step

🏋 GRPORelated to GRPORelated to GRPO

🐛 bugSomething isn't workingSomething isn't working

Status: Open.

#4669 In huggingface/trl;

· SonuDixit opened on Dec 11, 2025

CI fails with dev dependencies: AssertionError

🐛 bugSomething isn't workingSomething isn't working

Status: Open.

Bug

#4658 In huggingface/trl;

· albertvillanova opened on Dec 10, 2025

GRPOTrainer and bnb quantization configs are incomptiable

🏋 GRPORelated to GRPORelated to GRPO

🐛 bugSomething isn't workingSomething isn't working

Status: Open.

#4634 In huggingface/trl;

· JitheshPavan opened on Dec 6, 2025

[Bug] DeepSpeed ZeRO-2 is unstable with GRPOTrainer using Qwen3-VL MoE

Status: Open.

#4631 In huggingface/trl;

· casper-hansen opened on Dec 5, 2025

VLLM deprecated GuidedDecodingParams -&gt; StructuredOutputsParams

🏋 GRPORelated to GRPORelated to GRPO

🐛 bugSomething isn't workingSomething isn't working

🧒 good second issueGood for contributors with basic project familiarityGood for contributors with basic project familiarity

Status: Open.

#4617 In huggingface/trl;

· ed-pai opened on Dec 4, 2025