1. 15 May, 2024 1 commit
    • Daniël de Kok's avatar
      Add GPT-2 with flash attention (#1889) · b5bc6e5c
      Daniël de Kok authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      This change adds `FlashGPT2ForCausalLM` and wires it up. The model
      itself is pretty straightforward, the main difference from other models
      is that it uses trained position embeddings and that all weight matrices
      are transposed compared to other models (due to the use of Conv1D in the
      upstream model).
      
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [x] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [x] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [x] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [x] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      @Narsil 
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      b5bc6e5c
  2. 14 May, 2024 2 commits
  3. 13 May, 2024 2 commits
    • Nicolas Patry's avatar
      Granite support? (#1882) · d348d2b2
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      d348d2b2
    • Nicolas Patry's avatar
      Refactor layers. (#1866) · fd89d9df
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      fd89d9df
  4. 02 May, 2024 1 commit
    • Nicolas Patry's avatar
      Remove misleading warning (not that important nowadays anyway). (#1848) · de079d60
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      de079d60
  5. 01 May, 2024 1 commit
    • Nicolas Patry's avatar
      Fix: "Fixing" double BOS for mistral too. (#1843) · 27b3a2c9
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      27b3a2c9
  6. 30 Apr, 2024 1 commit
    • Nicolas Patry's avatar
      Small CI cleanup. (#1801) · 04d4765b
      Nicolas Patry authored
      # What does this PR do?
      
      Just unifying some branches and making intentions clearer (no cuda graph
      when 0 all the way in the launcher)
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      04d4765b
  7. 26 Apr, 2024 4 commits
    • Nicolas Patry's avatar
      Dummy CI run. (#1817) · e9f03f82
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      e9f03f82
    • Nicolas Patry's avatar
      Fixing qwen2. (#1818) · 8b8e8f66
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      8b8e8f66
    • Nicolas Patry's avatar
      Blunder (#1815) · a8fd4236
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      a8fd4236
    • Wang, Yi's avatar
      add intel xpu support for TGI (#1475) · 45ecf9d0
      Wang, Yi authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation
      
      ).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      
      ---------
      Signed-off-by: default avatarWang, Yi A <yi.a.wang@intel.com>
      Co-authored-by: default avatarMorgan Funtowicz <funtowiczmo@gmail.com>
      Co-authored-by: default avatarNicolas Patry <patry.nicolas@protonmail.com>
      45ecf9d0
  8. 25 Apr, 2024 1 commit
    • Nicolas Patry's avatar
      Use the generation config. (#1808) · ee47973a
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      ee47973a
  9. 23 Apr, 2024 2 commits
    • Nicolas Patry's avatar
      Idefics2. (#1756) · bfddfa59
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      bfddfa59
    • Nicolas Patry's avatar
      Phi3 support (#1797) · 986b4044
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      986b4044
  10. 22 Apr, 2024 1 commit
  11. 12 Apr, 2024 2 commits
  12. 10 Apr, 2024 2 commits
  13. 09 Apr, 2024 2 commits
    • Nicolas Patry's avatar
      Adding Llava-Next (Llava 1.6) with full support. (#1709) · 4634b00c
      Nicolas Patry authored
      # What does this PR do?
      
      - Changed all models to extract `embed_tokens` in order to enable llava
      to separately call the embeddings and the core model layers.
      - Added VlmCausalLM to inherit from FlashMistral in order to be
      maximally supported. The only added logics sits on top and parses images
      into pixel values, preallocates input_ids space for the image
      embeddings, and passes them for the model.
      - Added Clip for the vision tower.
      - Didn't add flash for the vision tower since there's no padding anyway.
      - Added heuristic (potentially incomplete) to calculate number of
      features *before* calculating the clip patches (allows for easier logic
      reuse of the LLM under the hood).
      
      
      Still needs to be done:
      
      - [x] Implement the image parsing in the controller side, to avoid
      downloading n times per TP shard and also refusing requests too large
      early and avoid issues where the truncation actually truncates the
      image.
      - [ ] Make sure it works with quantization properly.
      - [x] Make sure it works with TP>1
      
      
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      4634b00c
    • Nicolas Patry's avatar
      Automatic quantization config. (#1719) · 106d8ee8
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      106d8ee8
  14. 05 Apr, 2024 1 commit
  15. 04 Apr, 2024 1 commit
    • Nicolas Patry's avatar
      Add cuda graphs sizes and make it default. (#1703) · 99874eae
      Nicolas Patry authored
      # What does this PR do?
      
      ```
      text-generation-launcher --model-id XXX # Uses cuda graphs by default
      text-generation-launcher --model-id XXX --cuda-graphs "1,2"  #Restrict the number of cuda graphs which saves VRAM
      text-generation-launcher --model-id XXX --cuda-graphs "0"  # Disabling it entirely
      ```
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      99874eae
  16. 29 Mar, 2024 1 commit
  17. 22 Mar, 2024 2 commits
  18. 21 Mar, 2024 2 commits
    • Nicolas Patry's avatar
      Remove unecessary cuda graph. (#1664) · ed29d6ee
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      ed29d6ee
    • drbh's avatar
      feat: support force downcast after FastRMSNorm multiply for Gemma (#1658) · 6f15ac60
      drbh authored
      This PR adds `force_downcast_after` to `FastRMSNorm.forward` which is
      used in the Gemma model. References
      https://github.com/huggingface/transformers/pull/29402 and
      https://github.com/huggingface/transformers/pull/29729
      
      Setting `force_downcast_after=True` will perform the `hidden_states *
      weight` multiplication in f32 and then downcast to half. This differs
      slightly from the current implementation which first casts the
      `hidden_states` to a half and then multiples.
      6f15ac60
  19. 29 Feb, 2024 3 commits
    • drbh's avatar
      feat: accept legacy request format and response (#1527) · 3dd7da21
      drbh authored
      This WIP PR (will) add support for legacy OpenAI `v1/completions` API.
      
      This should allow TGI to be a drop in replacement for OpenAI when using
      tools that rely on the completions api
      
      Should fix:
      https://github.com/huggingface/text-generation-inference/issues/1468
      3dd7da21
    • Nicolas Patry's avatar
      Fix idefics default. (#1614) · 5a3903ba
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      5a3903ba
    • drbh's avatar
      fix: Handle concurrent grammar requests (#1610) · 343aa7a1
      drbh authored
      This PR fixes parallel grammar requests, currently grammar states are
      not concatenated correctly when a new request is added to the batch and
      this results in incorrect generation. This PR updates the `concatenate`
      function to correctly include the previous states.
      
      fixes: #1601
      343aa7a1
  20. 28 Feb, 2024 2 commits
  21. 26 Feb, 2024 1 commit
    • Nicolas Patry's avatar
      Revamp medusa implementation so that every model can benefit. (#1588) · bf700e7e
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      bf700e7e
  22. 21 Feb, 2024 1 commit
  23. 19 Feb, 2024 1 commit
    • Nicolas Patry's avatar
      Fix mistral with length > window_size for long prefills (rotary doesn't create... · d19c768c
      Nicolas Patry authored
      Fix mistral with length > window_size for long prefills (rotary doesn't create long enough cos, sin). (#1571)
      
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      d19c768c
  24. 16 Feb, 2024 1 commit
  25. 15 Feb, 2024 1 commit
    • drbh's avatar
      Outlines guided generation (#1539) · cef0553d
      drbh authored
      This WIP PR starts to add grammar support via outlines, currently this
      PR supports very simple regex grammars and does not optimize for
      precompiling or caching grammar fsm's.
      
      todo:
      - [X] add simple outlines guidance to `NextTokenChooser`
      - [X] update protos for grammar
      - [X] update generation params API
      - [X] constrain simple grammar
      - [ ] support parsing more complex grammar into fsm
      - [ ] support all outline support grammar types
      - [ ] explore optimizations to avoid recompiling grammars
      
      guided request
      ```bash
      curl -s 'http://localhost:3000/generate' \
      --header 'Content-Type: application/json' \
      --data-raw '{
          "inputs": "make an email for david: \n",
          "parameters": {
              "max_new_tokens": 6,
              "grammar": "[\\w-]+@([\\w-]+\\.)+[\\w-]+"
          }
      }' | jq
      ```
      response
      ```json
      {
        "generated_text": "david@example.com"
      }
      ```
      
      unguided request
      ```bash
      curl -s 'http://localhost:3000/generate' \
      --header 'Content-Type: application/json' \
      --data '{
          "inputs": "make an email for david: \n",
          "parameters": {
              "max_new_tokens": 6
          }
      }' | jq
      ```
      response
      ```json
      {
        "generated_text": "    email = 'david"
      }
      ```
      cef0553d
  26. 14 Feb, 2024 1 commit
    • Nicolas Patry's avatar
      Small cleanup. (#1560) · 4c2848b2
      Nicolas Patry authored
      Using a single `os.getenv` statement instead of multiple.
      Should make truthful values easier to catch
      
      In the end didn't move towards full CLI because modifying globals in
      Python is error prone (depends on code import order).
      
      Added an error when mamba is launched with TP.
      
      
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      4c2848b2