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

**URL:** <https://forum.modular.com/t/max-nightly-26-5-0-dev2026070915-mojo-1-0-0b3-dev2026070915-released/3306>\
**Category:** Nightly\
**Created:** [July 9, 2026, 6:17pm UTC](https://forum.modular.com/t/max-nightly-26-5-0-dev2026070915-mojo-1-0-0b3-dev2026070915-released/3306 "2026-07-09T18:17:06Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Modular](https://sea1.discourse-cdn.com/flex001/user_avatar/forum.modular.com/modular/32/17_2.png) [@Modular](https://forum.modular.com/u/Modular)\
**Post date:** [July 9, 2026, 6:17pm UTC](https://forum.modular.com/t/max-nightly-26-5-0-dev2026070915-mojo-1-0-0b3-dev2026070915-released/3306/1 "2026-07-09T18:17:06Z")

</div>

🧑‍🚀 A new nightly version has been released! 🧑‍🚀

See the quickstart guide for installation instructions: [Quickstart | Modular](https://docs.modular.com/max/get-started/#set-up-your-project)

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](https://github.com/modular/modular/compare/3e60d3078f2863193e940e9a3792c7ebb16e548b...fe806a55b6ee795e59b70a494d29c50db749c025))\>  
Current Mojo changelog: [https://github.com/modular/modular/blob/main/mojo/docs/nightly-changelog.md](https://github.com/modular/modular/blob/main/mojo/docs/nightly-changelog.md)