Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: huggingface/trl
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v0.20.0
Choose a base ref
...
head repository: huggingface/trl
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: v0.21.0
Choose a head ref
  • 18 commits
  • 63 files changed
  • 15 contributors

Commits on Jul 29, 2025

  1. ⬆️ Bump dev version (#3793)

    @qgallouedec
    qgallouedec authored Jul 29, 2025
    Configuration menu
    Copy the full SHA
    eb5d0fe View commit details
    Browse the repository at this point in the history

  2. Fix broken PEFT+TRL docs link in using_llama_models.md (#3794) 

    Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
    @bwook00 @kashif
    bwook00 and kashif authored Jul 29, 2025
    Configuration menu
    Copy the full SHA
    9269f9f View commit details
    Browse the repository at this point in the history

Commits on Jul 30, 2025

  1. 🐙 Add MPO VLM example script (#3799)

    @sergiopaniego
    sergiopaniego authored Jul 30, 2025
    Configuration menu
    Copy the full SHA
    25ce0f3 View commit details
    Browse the repository at this point in the history

  2. Examples list updated in docs (#3806)

    @sergiopaniego
    sergiopaniego authored Jul 30, 2025
    Configuration menu
    Copy the full SHA
    72bbc6d View commit details
    Browse the repository at this point in the history

  3. Add vLLM transformers backend to online methods (#3773) 

    Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: sergiopaniego <sergiopaniegoblanco@gmail.com>
    @merveenoyan @kashif @sergiopaniego
    3 people authored Jul 30, 2025
    Configuration menu
    Copy the full SHA
    90c7876 View commit details
    Browse the repository at this point in the history

  4. Correction parameter description (#3803) 

    Co-authored-by: lunzhongwang <lunzhongwang@soulapp.cn>
Co-authored-by: LeonEricsson <70749762+LeonEricsson@users.noreply.github.com>
    @1787648106 @LeonEricsson
    3 people authored Jul 30, 2025
    Configuration menu
    Copy the full SHA
    9a1e6a4 View commit details
    Browse the repository at this point in the history

Commits on Jul 31, 2025

  1. Add GSPO script examples (VLM/LLM) (#3810)

    @sergiopaniego
    sergiopaniego authored Jul 31, 2025
    Configuration menu
    Copy the full SHA
    3ae60cd View commit details
    Browse the repository at this point in the history

  2. add xpu support for mergekit (#3800) 

    Signed-off-by: Yao, Matrix <matrix.yao@intel.com>
    @yao-matrix
    yao-matrix authored Jul 31, 2025
    Configuration menu
    Copy the full SHA
    ab24000 View commit details
    Browse the repository at this point in the history

  3. GSPO parameters update from v2 (#3798) 

    Co-authored-by: LeonEricsson <70749762+LeonEricsson@users.noreply.github.com>
Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
    @BounharAbdelaziz @LeonEricsson @qgallouedec
    3 people authored Jul 31, 2025
    Configuration menu
    Copy the full SHA
    79c5797 View commit details
    Browse the repository at this point in the history

  4. Fix citation

    @qgallouedec
    qgallouedec committed Jul 31, 2025
    Configuration menu
    Copy the full SHA
    294e8cb View commit details
    Browse the repository at this point in the history

  5. fix CI docs and grpo slow test (#3814) 

    Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
    @kashif @qgallouedec
    kashif and qgallouedec authored Jul 31, 2025
    Configuration menu
    Copy the full SHA
    dbbc770 View commit details
    Browse the repository at this point in the history

Commits on Aug 1, 2025

  1. Performance optimization: Replace list comprehensions with tensor ope… 

    …rations in BCO and KTO trainers (#3813)

Co-authored-by: chiliu <chiliu@paypal.com>
    @chi2liu
    chi2liu and chiliu authored Aug 1, 2025
    Configuration menu
    Copy the full SHA
    ead5aaf View commit details
    Browse the repository at this point in the history

  2. Improve trainer doc (#3818)

    @qgallouedec
    qgallouedec authored Aug 1, 2025
    Configuration menu
    Copy the full SHA
    072d7dd View commit details
    Browse the repository at this point in the history

Commits on Aug 4, 2025

  1. Add 'Post training a VLM for reasoning with GRPO using TRL' recipe to… 

    … Community tutorials (#3843)
    @sergiopaniego
    sergiopaniego authored Aug 4, 2025
    Configuration menu
    Copy the full SHA
    6776376 View commit details
    Browse the repository at this point in the history

Commits on Aug 5, 2025

  1. [GRPO]: Fix Entropy Mask Threshold Calculation when using Multi-GPU t… 

    …raining (#3833)

Co-authored-by: LeonEricsson <70749762+LeonEricsson@users.noreply.github.com>
    @pramodith @LeonEricsson
    pramodith and LeonEricsson authored Aug 5, 2025
    Configuration menu
    Copy the full SHA
    5d914a4 View commit details
    Browse the repository at this point in the history

  2. 🪦 Remove deprecated (#3817) 

    Co-authored-by: LeonEricsson <70749762+LeonEricsson@users.noreply.github.com>
    @qgallouedec @LeonEricsson
    qgallouedec and LeonEricsson authored Aug 5, 2025
    Configuration menu
    Copy the full SHA
    21060b2 View commit details
    Browse the repository at this point in the history

  3. 🌺 OpenAI GPT OSS & Harmony support (#3848) 

    Co-authored-by: Shirin Yamani <75791599+shirinyamani@users.noreply.github.com>
Co-authored-by: Sergio Paniego Blanco <sergiopaniegoblanco@gmail.com>
    @qgallouedec @shirinyamani @sergiopaniego
    3 people authored Aug 5, 2025
    Configuration menu
    Copy the full SHA
    17393b8 View commit details
    Browse the repository at this point in the history

  4. Release: v0.21 (#3849)

    @qgallouedec
    qgallouedec authored Aug 5, 2025
    Configuration menu
    Copy the full SHA
    46d09bd View commit details
    Browse the repository at this point in the history
Loading