Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[DRAFT] Compatibility Matrix #140

Closed
wants to merge 19 commits into from
Closed

[DRAFT] Compatibility Matrix #140

wants to merge 19 commits into from

Commits on Sep 13, 2024

  1. [CI/Build] Enable InternVL2 PP test only on single node (vllm-project… 

    …#8437)
    @Isotr0py
    Isotr0py authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    9b4a3b2 View commit details
    Browse the repository at this point in the history

  2. [doc] recommend pip instead of conda (vllm-project#8446)

    @youkaichao
    youkaichao authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    cab69a1 View commit details
    Browse the repository at this point in the history

  3. [Misc] Skip loading extra bias for Qwen2-VL GPTQ-Int8 (vllm-project#8442 

    )
    @jeejeelee
    jeejeelee authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    06311e2 View commit details
    Browse the repository at this point in the history

  4. [misc][ci] fix quant test (vllm-project#8449)

    @youkaichao
    youkaichao authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    a246912 View commit details
    Browse the repository at this point in the history

  5. [Installation] Gate FastAPI version for Python 3.8 (vllm-project#8456)

    @DarkLight1337
    DarkLight1337 authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    ecd7a1d View commit details
    Browse the repository at this point in the history

  6. [plugin][torch.compile] allow to add custom compile backend (vllm-pro… 

    …ject#8445)
    @youkaichao
    youkaichao authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    0a4806f View commit details
    Browse the repository at this point in the history

  7. [CI/Build] Reorganize models tests (vllm-project#7820)

    @DarkLight1337
    DarkLight1337 authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    a84e598 View commit details
    Browse the repository at this point in the history

  8. [Doc] Add oneDNN installation to CPU backend documentation (vllm-proj… 

    …ect#8467)
    @Isotr0py
    Isotr0py authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    f57092c View commit details
    Browse the repository at this point in the history

  9. [HotFix] Fix final output truncation with stop string + streaming (vl… 

    …lm-project#8468)
    @njhill
    njhill authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    18e9e1f View commit details
    Browse the repository at this point in the history

  10. bump version to v0.6.1.post2 (vllm-project#8473)

    @simon-mo
    simon-mo authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    9ba0817 View commit details
    Browse the repository at this point in the history

  11. [Hardware][intel GPU] bump up ipex version to 2.3 (vllm-project#8365) 

    Co-authored-by: Yan Ma <yan.ma@intel.com>
    @jikunshang @yma11
    jikunshang and yma11 authored Sep 13, 2024
    Configuration menu
    Copy the full SHA
    8517252 View commit details
    Browse the repository at this point in the history

Commits on Sep 14, 2024

  1. [Kernel][Hardware][Amd]Custom paged attention kernel for rocm (vllm-p… 

    …roject#8310)
    @charlifu
    charlifu authored Sep 14, 2024
    Configuration menu
    Copy the full SHA
    1ef0d2e View commit details
    Browse the repository at this point in the history

  2. [Model] support minicpm3 (vllm-project#8297) 

    Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
    @SUDA-HLT-ywfang @DarkLight1337
    SUDA-HLT-ywfang and DarkLight1337 authored Sep 14, 2024
    Configuration menu
    Copy the full SHA
    8a0cf1d View commit details
    Browse the repository at this point in the history

  3. [torch.compile] fix functionalization (vllm-project#8480)

    @youkaichao
    youkaichao authored Sep 14, 2024
    Configuration menu
    Copy the full SHA
    a36e070 View commit details
    Browse the repository at this point in the history

  4. [torch.compile] add a flag to disable custom op (vllm-project#8488)

    @youkaichao
    youkaichao authored Sep 14, 2024
    Configuration menu
    Copy the full SHA
    47790f3 View commit details
    Browse the repository at this point in the history

  5. [TPU] Implement multi-step scheduling (vllm-project#8489)

    @WoosukKwon
    WoosukKwon authored Sep 14, 2024
    Configuration menu
    Copy the full SHA
    50e9ec4 View commit details
    Browse the repository at this point in the history

Commits on Sep 15, 2024

  1. [Bugfix][Model] Fix Python 3.8 compatibility in Pixtral model by upda… 

    …ting type annotations (vllm-project#8490)
    @chrisociepa
    chrisociepa authored Sep 15, 2024
    Configuration menu
    Copy the full SHA
    3724d5f View commit details
    Browse the repository at this point in the history

  2. [Bugfix][Kernel] Add IQ1_M quantization implementation to GGUF kern… 

    …el (vllm-project#8357)
    @Isotr0py
    Isotr0py authored Sep 15, 2024
    Configuration menu
    Copy the full SHA
    fc990f9 View commit details
    Browse the repository at this point in the history

Commits on Sep 16, 2024

  1. [Doc] Compatibility matrix for mutual exclusive features 

    Signed-off-by: Wallas Santos <wallashss@ibm.com>
    @wallashss
    wallashss committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    e72169b View commit details
    Browse the repository at this point in the history