-
Notifications
You must be signed in to change notification settings - Fork 2.9k
Pull requests: huggingface/trl
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Revert xfail for MoE LoRA tests now that peft#3602 fixed the autocast dtype bug
#6919
opened Aug 25, 2026 by
albertvillanova
Member
Loading…
Document how to change the training objective by subclassing a trainer
#6918
opened Aug 25, 2026 by
sergiopaniego
Member
Loading…
4 of 8 tasks
Retry tests failing on cuBLAS allocation errors the rerun filter missed
#6916
opened Aug 25, 2026 by
albertvillanova
Member
Loading…
Fix: vLLM weight sync fails instead of hanging
#6913
opened Aug 25, 2026 by
AmineDiro
Member
Loading…
Add a test for the SFT trainer quantization_config argument
#6911
opened Aug 25, 2026 by
albertvillanova
Member
Loading…
Add a QLoRA test to the GRPO test suite
#6910
opened Aug 25, 2026 by
albertvillanova
Member
Loading…
Add a QLoRA test to the GRPO VLM test suite
#6909
opened Aug 25, 2026 by
albertvillanova
Member
Loading…
Read the job status from the job context in the local Slack action
#6908
opened Aug 25, 2026 by
albertvillanova
Member
•
3/3
Loading…
fix(vllm): support IPv6 communicator hosts
#6907
opened Aug 25, 2026 by
yikun-c
Loading…
4 of 8 tasks
Support tool-returned images across VLM architectures
#6906
opened Aug 25, 2026 by
DaoyuanLi2816
Contributor
Loading…
3 of 8 tasks
Read the Slack channel from the environment in the local Slack action
#6904
opened Aug 25, 2026 by
albertvillanova
Member
•
2/3
Loading…
Post the Docker image build results to the shared CI Slack channel
#6903
opened Aug 25, 2026 by
albertvillanova
Member
•
1/3
Loading…
1 task
Require bitsandbytes>=0.50.0 and drop the _check_is_size warning filter
#6893
opened Aug 24, 2026 by
behroozazarkhalili
Collaborator
Loading…
Warn when truncated sampling biases the vLLM importance-sampling ratio
#6880
opened Aug 23, 2026 by
behroozazarkhalili
Collaborator
Loading…
fix(data): unpair IterableDatasetDict inputs
#6878
opened Aug 23, 2026 by
YZJF
Loading…
5 of 8 tasks
pin fastapi>=0.133 in vllm extra to match vllm requirement
#6876
opened Aug 23, 2026 by
hxm2023
Loading…
6 of 8 tasks
Fix CLI handling of --accelerate_config=<name>
#6875
opened Aug 23, 2026 by
YZJF
Loading…
3 of 8 tasks
Fix MFU helpers for configs without KV head count
#6871
opened Aug 23, 2026 by
DaoyuanLi2816
Contributor
Loading…
3 of 8 tasks
Target the Mamba in_proj in the Nemotron 3 LoRA example
#6870
opened Aug 22, 2026 by
behroozazarkhalili
Collaborator
Loading…
Add expert-parallelism example: SFT of 100B-753B MoE models
#6869
opened Aug 22, 2026 by
qgallouedec
Member
•
Draft
Handle None token logprobs from vLLM in AsyncGRPOTrainer
#6868
opened Aug 22, 2026 by
rajathpi
Loading…
3 of 8 tasks
Drop the dead gate_proj LoRA target from the Nemotron 3 SFT example
#6866
opened Aug 22, 2026 by
behroozazarkhalili
Collaborator
Loading…
Do the chunked-CE
lm_head projection on tensor cores instead of in fp32
#6863
opened Aug 21, 2026 by
qgallouedec
Member
•
1/2
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-07-25.