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: France-Travail/happy_vllm
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v1.1.9
Choose a base ref
...
head repository: France-Travail/happy_vllm
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: release
Choose a head ref
  • 16 commits
  • 23 files changed
  • 6 contributors

Commits on Sep 17, 2024

  1. Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    59dba5f View commit details

Commits on Oct 28, 2024

  1. Update 062 (#46)

    * Updated vllm to 0.6.1
    
    * Forgot some changes
    
    * Changes to take into account mistral tokenizers
    
    * Updated to 0.6.1.post1
    
    * switch old rpc implementation by new one
    
    * remove engine forme serve_http
    
    * switch get_model_config_rpc to get_model_config
    
    * fix model name with name and not modelpath
    
    * add new args 0.6.2 vllm and fix test
    
    * Fix gauge metrics
    
    * fix mypy
    
    * fix mpy
    
    * Fix pytest
    
    * force 0.6.2
    
    * undo version vllm
    
    * Updated requirements.txt and pyproject.toml
    
    * Fix async_engine args + unit test
    
    * update rpc_server to mp_engine name and import + fix model_config dupplication
    
    * Add disable_fastapi_docs argument and update decalre_application
    
    * fix conftest argument unit tests
    
    ---------
    
    Co-authored-by: Gautier Solard <[email protected]>
    maxDavid40 and gsolard authored Oct 28, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    4f45ccc View commit details

Commits on Oct 29, 2024

  1. Update 063 (#47)

    * Updated vllm to 0.6.1
    
    * Forgot some changes
    
    * Changes to take into account mistral tokenizers
    
    * Updated to 0.6.1.post1
    
    * switch old rpc implementation by new one
    
    * remove engine forme serve_http
    
    * switch get_model_config_rpc to get_model_config
    
    * fix model name with name and not modelpath
    
    * add new args 0.6.2 vllm and fix test
    
    * Fix gauge metrics
    
    * fix mypy
    
    * fix mpy
    
    * Fix pytest
    
    * force 0.6.2
    
    * undo version vllm
    
    * update vllm version + add new engine arguments + update unit tests
    
    * Fix prometheus memory metric with num_scheduler_steps > 1
    
    * Updated requirements.txt and pyproject.toml
    
    * Fix async_engine args + unit test
    
    * update rpc_server to mp_engine name and import + fix model_config dupplication
    
    * Update use_v2_block_manager value
    
    * fix import
    
    * fix import v2
    
    * Fix import + add socket bind + tool parser plugin import
    
    * Add validate_parsed_serve_args function in launch_app
    
    ---------
    
    Co-authored-by: Gautier Solard <[email protected]>
    maxDavid40 and gsolard authored Oct 29, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    ec4b4cf View commit details
  2. version 1.1.10

    DAVID Max committed Oct 29, 2024
    Copy the full SHA
    9c5587a View commit details
  3. go to 1.1.11 (#48)

    maxDavid40 authored Oct 29, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    8c23233 View commit details

Commits on Nov 21, 2024

  1. Update 064 (#49)

    * Update vllm 064
    
    * add enable_prompt_tokens_details argument
    
    * Fix logger missing
    
    * use_v2_block_manager default value
    
    * Updated dependances
    
    * Add sock.close()
    
    ---------
    
    Co-authored-by: Gautier Solard <[email protected]>
    maxDavid40 and gsolard authored Nov 21, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    3b598a8 View commit details
  2. version 1.1.11

    maxDavid40 committed Nov 21, 2024
    Copy the full SHA
    b87a56d View commit details
  3. version 1.1.11

    maxDavid40 committed Nov 21, 2024
    Copy the full SHA
    869bb57 View commit details
  4. version 1.1.11

    maxDavid40 committed Nov 21, 2024
    Copy the full SHA
    89ae67e View commit details
  5. increment version (#50)

    maxDavid40 authored Nov 21, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    37aacae View commit details

Commits on Dec 12, 2024

  1. upgrade version of upload artifact action (#51)

    * upgrade version of upload artifact action
    
    * Added overwrite
    
    ---------
    
    Co-authored-by: Gautier Solard <[email protected]>
    mfournioux and gsolard authored Dec 12, 2024

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    7ac9b58 View commit details

Commits on Jan 6, 2025

  1. Update to 0.6.6.post1 (#52)

    * Update to 0.6.6.post1
    
    * Add doc for the new application arguments
    
    * Changed the place of load_chat_template
    
    * Added with_cancellation
    
    * Fixed MockOpenAIServingTokenization
    gsolard authored Jan 6, 2025

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    95e53e7 View commit details
  2. Copy the full SHA
    1486175 View commit details
  3. Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    4d77ab1 View commit details

Commits on Jan 16, 2025

  1. Add embeddings (#54)

    * Added embeddings
    
    * Functionnal embeddings
    
    * Added doc and protection depending on the task
    gsolard authored Jan 16, 2025

    Verified

    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    Copy the full SHA
    e4383a2 View commit details
  2. Copy the full SHA
    8a299bd View commit details
Loading