MAX Nightly 26.5.0.dev2026070915 (Mojo 1.0.0b3.dev2026070915) Released

Nightly
1

:astronaut: A new nightly version has been released! :astronaut:

See the quickstart guide for installation instructions: Quickstart | Modular

MAX changelog updates:

  • Fixed the code label on the maxserve_request_count metric so it reports
    the HTTP status code actually returned to the client. The count is now
    recorded from the HTTP layer, so failures rejected before generation (for
    example a request with an unreachable image URL) are counted with their real
    status code instead of being labeled 200 or dropped entirely. Liveness and
    observability endpoints (/health, /version, /ping, /metrics) are not
    counted.
  • Failed request submissions in the OpenAI-compatible serving endpoints now
    surface as HTTP error responses instead of a 200 OK streaming response that
    carries an error payload. Request tokenization and the handoff to the model
    worker now complete before the streaming response headers are sent, so a
    failure at submission time (for example, a dead model worker) maps to an HTTP
    5xx (or 4xx for input errors). Errors that occur mid-stream, after the first
    chunk has been sent, are still serialized as an error event within the stream.
  • Added a max-benchmark conda package for parity with the max[benchmark]
    wheel extra.
  • Added max.graph.ops.floor_div (and F.floor_div), element-wise floor
    division matching Python //. Unlike ops.div, integer operands stay in
    the integer domain instead of being promoted to float64, so integer floor
    division compiles on backends without 64-bit float support (for example,
    Metal GPUs).

Mojo changelog updates:

  • [MLRT][Metal] Add programmatic GPU frame capture and print control
  • [stdlib] deprecate UnsafePointer.init_pointee methods in favor of unsafe_write variants.
  • [mojo] Normalize conditional comptime members in method signatures
  • [mojo-lsp] Flip LSP docstring check flag to false by default
  • [stdlib] Relax LinkedList insert/extend to not require ImplicitlyDeletable
  • [stdlib] Implement warp.vote (ballot) for Apple GPU

Raw MAX diff: https://github.com/modular/modular/compare/3e60d3078f2863193e940e9a3792c7ebb16e548b...fe806a55b6ee795e59b70a494d29c50db749c025)>
Current Mojo changelog: https://github.com/modular/modular/blob/main/mojo/docs/nightly-changelog.md