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: fastmachinelearning/pytorch_backend
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: main
Choose a base ref
...
head repository: triton-inference-server/pytorch_backend
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: main
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 8 commits
  • 13 files changed
  • 3 contributors

Commits on Oct 9, 2025

  1. docs: Update README to reflect torch 2 support (triton-inference-serv…

    …er#160)
    
    Update the README file to remove the "experimental" tag from the documentaion.
    
    The existance of the tag was an oversight as Torch 2.x has been supported for 18+ months at this point.
    
    Signed-off-by: J Wyman <[email protected]>
    whoisj authored Oct 9, 2025
    Configuration menu
    Copy the full SHA
    abafeb6 View commit details
    Browse the repository at this point in the history

Commits on Oct 10, 2025

  1. Protect thread setting call (triton-inference-server#159)

    * use call_once to prevent repeated thread count setting
    
    * update docs for thread parameters
    
    * always emit a message with number of threads
    
    * apply formatting
    
    * readme formatting
    kpedro88 authored Oct 10, 2025
    Configuration menu
    Copy the full SHA
    b855365 View commit details
    Browse the repository at this point in the history

Commits on Oct 14, 2025

  1. docs: Improve README (triton-inference-server#161)

    * docs: Improve README
    
    Update the README file to improve readability, clarity, and markdown formatting standards.
    
    Cleaned up and improvements were applied to the document:
    
    - Correctly indented content within bullet-point lists.
    - Used GitHub flavored markdown to enable NOTE, TIP, etc. callouts where appropriate.
    - Reflowed text to use the more standard new-line after every sentance style.
    - Replaced works this "this", "here", and "link" with more descriptive terms for link text.
    - Corrected the format of the pbtxt examples.
    - Updated the recommended pytorch container from NGC.
    
    * fixup: Resolve Code Review
    
    * docs: Additional Improvements
    
    Use yaml instead of proto for code blocks to improve readability.
    
    Add example instance_group configuration.
    
    * revert: proto -> yaml markup
    whoisj authored Oct 14, 2025
    Configuration menu
    Copy the full SHA
    6d02d35 View commit details
    Browse the repository at this point in the history

Commits on Oct 29, 2025

  1. docs: Correct README Instructions (triton-inference-server#164)

    This change corrects the instruction for how to use PyTorch 2 with the backend.
    whoisj authored Oct 29, 2025
    Configuration menu
    Copy the full SHA
    92692f8 View commit details
    Browse the repository at this point in the history

Commits on Nov 3, 2025

  1. Adding libtorch_nvshmem.so (triton-inference-server#162) (triton-infe…

    …rence-server#166)
    
    * Adding libtorch_nvshmem.so
    
    * change: CPU only build doesn't have CUDA_VERSION environment variable. Using flag to control library inclusion.
    
    * Removing generation expression
    mc-nv authored Nov 3, 2025
    Configuration menu
    Copy the full SHA
    a95f663 View commit details
    Browse the repository at this point in the history

Commits on Nov 4, 2025

  1. Configuration menu
    Copy the full SHA
    45bd8e5 View commit details
    Browse the repository at this point in the history
  2. maintenance: Separate Code into Separate Files (triton-inference-serv…

    …er#163)
    
    * maintenance: Separate Code into Separate Files
    
    This change breaks the monolithic src/libtorch.cc into multiple files,
    with a modern separation of classes into separate header and code files.
    
    * Accept Rename
    
    Renamed 'string_utilities.*' to 'string_utils.*' as requested.
    whoisj authored Nov 4, 2025
    Configuration menu
    Copy the full SHA
    cb9336c View commit details
    Browse the repository at this point in the history

Commits on Nov 5, 2025

  1. build(fix): Update header file reference (triton-inference-server#170)

    * Update header file reference
    
    * fix: address pre-commit issue
    
    * Update header name
    mc-nv authored Nov 5, 2025
    Configuration menu
    Copy the full SHA
    7e9d0f9 View commit details
    Browse the repository at this point in the history
Loading