[{"url":"https://api.github.com/repos/modular/modular/releases/368691898","assets_url":"https://api.github.com/repos/modular/modular/releases/368691898/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/368691898/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/max/v26.5.0","id":368691898,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4V-cq6","tag_name":"max/v26.5.0","target_commitish":"max/v26.5","name":"MAX 26.5 / Mojo 1.0.0","draft":false,"immutable":false,"prerelease":false,"created_at":"2026-08-11T15:13:55Z","updated_at":"2026-08-11T16:38:07Z","published_at":"2026-08-11T16:05:56Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/max/v26.5.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/max/v26.5.0","body":"In this release, we've moved most of the GPU programming APIs out of the Mojo standard library and into a new top-level `max` package—`std.algorithm` is now `max.algorithm`, `std.benchmark` is `max.benchmark`, and `std.gpu.{compute,host,memory,sync}` is `max.gpu.*`, along with the Mojo `layout` package. All of which is now part of the new [MAX accelerator library](https://docs.modular.com/api/mojo/), which also includes the existing AI kernels. We've also extended Apple silicon GPU support back to M1 devices, and added hardware-MMA flash-attention prefill for M5 to speed up TTFT. The MAX model bring-up workflow also gains new agent skills in [our skills repo](https://github.com/modular/skills), including new `serve-model`, `benchmark-model`, `eval-model`, and `profile-model` skills. We've also expanded model coverage and capabilities, made significant strides speeding up the Python API's experimental eager interpreter, sped up various kernels across NVIDIA, AMD, and Apple GPUs, and much more to accelerate models served with MAX.\r\n\r\nOf course, this release also brings Mojo 1.0! 🔥\r\n\r\nWith Mojo 1.0, we've started marking standard library APIs as stable, which means they won't be removed or changed in ways that break compatibility—we started with a small set that we'll grow in subsequent 1.x releases. There are so many changes in this release, it's difficult to summarize. It includes lambdas, pointer unification, interior origins, required `var` declarations, constraint improvements, faster Python interop, and so much more. We worked hard on getting names, defaults, and safety boundaries right for 1.0. That does mean you'll find more breaking changes than usual in this release. But nearly every breaking change ships with a deprecated alias and a compiler fix-it, so migration is mechanical.\r\n\r\nCheck out all the updates with the full [MAX release notes](https://docs.modular.com/releases/v26.5/) and [Mojo release notes](https://mojolang.org/releases/v1.0.0/).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/368691898/reactions","total_count":67,"+1":23,"-1":0,"laugh":0,"hooray":28,"confused":0,"heart":5,"rocket":11,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/341516225","assets_url":"https://api.github.com/repos/modular/modular/releases/341516225/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/341516225/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/max/v26.4.0","id":341516225,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4UWx_B","tag_name":"max/v26.4.0","target_commitish":"max/v26.4","name":"MAX 26.4 / Mojo 1.0.0b2","draft":false,"immutable":false,"prerelease":false,"created_at":"2026-06-18T15:56:24Z","updated_at":"2026-06-18T17:05:06Z","published_at":"2026-06-18T16:15:54Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/max/v26.4.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/max/v26.4.0","body":"The MAX 26.4 release brings Apple silicon GPU serving to almost all compatible MAX models, with M3 and newer devices now running Llama and Qwen model families (and others that fit in system memory). We've also added support for new models, including Tencent Hunyuan Hy3-preview, LiquidAI LFM2, and GLM-5/5.1 with FP8/NVFP4 weights. DeepSeek V2 and V3 can now run on a single GPU (with block-scaled FP8 quantization for V3) and long-context sparse MLA for DeepSeek-V3.2. Gemma 4 gains native FP8 attention with an FP8 KV cache on B200 (roughly matching bf16 accuracy while doubling KV cache capacity) and NVFP4 quantization, structured output with grammar enforcement, MTP speculative decoding, and multi-GPU support for the 31B variant. MiniMax-M2 picks up MXFP4 quantization and tensor-parallel attention combined with expert-parallel MoE (TP+EP). Plus much, much more, including enhanced Prometheus metrics, improved kernel performance, new benchmark datasets, and lots of Python API upgrades.\r\n\r\nThe Mojo 1.0 beta 2 (v1.0.0b2) release makes steady progress towards a stable 1.0 release later this year. It removes the requirement that collection elements be `Copyable`: `List`, `Deque`, `LinkedList`, `InlineArray`, `Dict`, and `Set` now accept move-only elements. Trailing `where` clauses are now supported on struct declarations and `comptime` alias declarations. `String` and `StringSlice` gain Unicode-aware subscripts. The `fn` function declarations are now a hard compilation error (completing the `def`/`fn` unification begun in beta 1). Implicit `std` imports are also an error, making all standard-library dependencies explicit and freeing common names like `algorithm` and `memory` for user modules. On the CLI side, `mojo package` renamed to `mojo precompile` and the `.mojopkg` extension renamed to `.mojoc` (which is also a smaller, faster format). And that's just the start of it.\r\n\r\nFor much more detail about the MAX and Mojo changes, see the [MAX changelog](https://docs.modular.com/max/changelog/#v264-2026-06-18) and [Mojo changelog](https://mojolang.org/releases/v1.0.0b2/).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/341516225/reactions","total_count":6,"+1":2,"-1":0,"laugh":0,"hooray":1,"confused":0,"heart":0,"rocket":3,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/319042992","assets_url":"https://api.github.com/repos/modular/modular/releases/319042992/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/319042992/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/max/v26.3.0","id":319042992,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4TBDWw","tag_name":"max/v26.3.0","target_commitish":"max/v26.3","name":"MAX 26.3 / Mojo 1.0.0b1","draft":false,"immutable":false,"prerelease":false,"created_at":"2026-05-07T15:46:55Z","updated_at":"2026-05-07T16:16:20Z","published_at":"2026-05-07T16:11:03Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/max/v26.3.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/max/v26.3.0","body":"The Modular 26.3 release brings video generation to MAX with Wan 2.1 / 2.2 diffusion models (image-to-video and video-to-video), a new multi-GPU Python API via `max.experimental.sharding` that distributes models across a DeviceMesh with Replicated, Sharded, and Partial placement primitives, and NVFP4 grouped matmul kernels that now outperform FlashInfer on B200 for Kimi K2.5. New model support lands for Gemma 4 with multimodal vision, Qwen3 and Qwen3-VL (including MoE variants), MiniMax-M2 with 4×H100 multi-GPU serving, and FLUX.2 with TaylorSeer and TeaCache denoising caches for faster image-to-image generation.\r\n\r\nThe Mojo 1.0 beta 1 (v1.0.0b1) release introduces type refinement from compile-time assumptions: where `conforms_to(T, Trait)` clauses, `comptime if`, and `comptime assert` now narrow types automatically, eliminating the need for manual `trait_downcast` calls throughout the standard library. Closure unification advances further—stateless closures auto-lift to function pointers, the `ref` capture convention is supported, and the new thin function effect cleanly distinguishes function pointer types from closure traits. The `fn` keyword now emits a deprecation warning (becoming a hard error next release), negative indexing on standard collections has been removed in favor of cheap CPU bounds checks that are now on by default, and `UnsafePointer` is non-null by design with nullability expressed via `Optional[UnsafePointer[...]]`.\r\n\r\nCheck out all the updates with the full [MAX changelog](https://docs.modular.com/stable/max/changelog/#v263-2026-05-07263-2026-05-07) and [Mojo changelog](https://mojolang.org/releases/v1.0.0b1/).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/319042992/reactions","total_count":26,"+1":8,"-1":0,"laugh":0,"hooray":8,"confused":0,"heart":4,"rocket":6,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/299034558","assets_url":"https://api.github.com/repos/modular/modular/releases/299034558/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/299034558/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/modular/v26.2.0","id":299034558,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4R0ue-","tag_name":"modular/v26.2.0","target_commitish":"modular/v26.2","name":"Modular 26.2","draft":false,"immutable":false,"prerelease":false,"created_at":"2026-03-19T15:57:18Z","updated_at":"2026-03-19T16:33:27Z","published_at":"2026-03-19T15:59:53Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/modular/v26.2.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/modular/v26.2.0","body":"The 26.2 release brings image generation to MAX with FLUX diffusion models served through a new `/v1/responses` endpoint implementing the OpenResponses API. This release also delivers major DeepSeek improvements—DeepSeekV3.2 with multi-latent attention, NVFP4 quantization for DeepSeek-R1, and simplified single-node expert parallelism—alongside new model support for Kimi vision-language models and Qwen3-MoE.\r\n\r\nThis release deprecates Mojo's `fn` keyword, unifying all function declarations into the `def` keyword, and merges `__moveinit__`/`__copyinit__` into a unified `__init__()` with `take`/`copy` arguments. New language features include conditional trait conformances via `where` clauses, t-strings for structured template processing, `comptime if`/`comptime for` syntax, a Python-style `assert` statement, and much more.\r\n\r\nCheck out all of 26.2's updates with the full [MAX changelog](https://docs.modular.com/max/changelog/#v262-2026-03-19) and [Mojo changelog](https://docs.modular.com/mojo/changelog/#v0262-2026-03-19).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/299034558/reactions","total_count":14,"+1":4,"-1":0,"laugh":0,"hooray":5,"confused":0,"heart":2,"rocket":2,"eyes":1}},{"url":"https://api.github.com/repos/modular/modular/releases/281224854","assets_url":"https://api.github.com/repos/modular/modular/releases/281224854/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/281224854/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/modular/v26.1.0","id":281224854,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4QwyaW","tag_name":"modular/v26.1.0","target_commitish":"modular/v26.1","name":"Modular 26.1","draft":false,"immutable":false,"prerelease":false,"created_at":"2026-01-29T17:14:32Z","updated_at":"2026-01-29T18:21:09Z","published_at":"2026-01-29T18:21:09Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/modular/v26.1.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/modular/v26.1.0","body":"This release graduates the eager-style `Tensor` and `Module` APIs out of\r\nexperimental, offering a PyTorch-like modeling interface for building\r\nhigh-performance GenAI models—simplifying the process to deploy a model in\r\nproduction with MAX. This release also expands Apple silicon GPU support so\r\nbasic MAX graphs now compile and run on Apple GPUs (LLM inference support is\r\ncoming in future updates).\r\n\r\n26.1 also includes several new Mojo language features, such as compile-time\r\nreflection for automatic trait conformance (enabling things like JSON\r\nserialization and CLI argument parsing), explicitly destroyed types (\"linear\r\ntypes\") for compile-time guarantees that values cannot be leaked, and typed\r\nerrors for better error-handling on GPUs without overhead.\r\n\r\nCheck out all of 26.1's updates with the full [MAX changelog](https://docs.modular.com/max/changelog#v261-2026-01-29) and [Mojo changelog](https://docs.modular.com/mojo/changelog#v0261-2026-01-29).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/281224854/reactions","total_count":23,"+1":7,"-1":0,"laugh":0,"hooray":6,"confused":0,"heart":4,"rocket":6,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/264065623","assets_url":"https://api.github.com/repos/modular/modular/releases/264065623/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/264065623/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/modular/v25.7.0","id":264065623,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4PvVJX","tag_name":"modular/v25.7.0","target_commitish":"main","name":"Modular 25.7","draft":false,"immutable":false,"prerelease":false,"created_at":"2025-11-20T06:32:38Z","updated_at":"2025-11-20T17:18:14Z","published_at":"2025-11-20T17:17:51Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/modular/v25.7.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/modular/v25.7.0","body":"The 25.7 release delivers a fully open-source MAX Python API, an experimental PyTorch-like Model API for faster, easier development and compilation, and major performance and portability gains including bfloat16 on Grace Hopper and Grace Blackwell. Mojo also sees significant upgrades with expanded Apple silicon GPU coverage and safer GPU programming features like stricter type checking, improved pointers, clearer error messages, and better Address Sanitizer support.\r\nCheck out all of 25.7's updates with the full [MAX changelog](https://docs.modular.com/max/changelog/) and [Mojo changelog](https://docs.modular.com/mojo/changelog/).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/264065623/reactions","total_count":11,"+1":8,"-1":0,"laugh":0,"hooray":0,"confused":0,"heart":3,"rocket":0,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/249101992","assets_url":"https://api.github.com/repos/modular/modular/releases/249101992/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/249101992/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/modular/v25.6.0","id":249101992,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4O2P6o","tag_name":"modular/v25.6.0","target_commitish":"modular/v25.6","name":"Modular 25.6","draft":false,"immutable":false,"prerelease":false,"created_at":"2025-09-22T16:40:46Z","updated_at":"2025-09-22T16:45:26Z","published_at":"2025-09-22T16:45:26Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/modular/v25.6.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/modular/v25.6.0","body":"The 25.6 release is a major milestone in our mission to build a unified compute layer for AI. MAX offers a model serving framework that now spans from consumer CPUs and GPUs to the world's most powerful datacenter GPUs, now including industry leading throughput on both NVIDIA Blackwell (B200) and AMD MI355X. We've also added a `max benchmark` command to our CLI tool that makes it easy to verify all our performance benefits for yourself.\r\n\r\nPlus, support for Apple Silicon GPUs is well on its way. For the first time, Mojo developers can directly tap into Mac GPUs—allowing you to write GPU algorithms that run unmodified across Apple Silicon GPUs, NVIDIA Blackwell, AMD MI325X, AMD MI355X, and more. On top of that, you can also now `pip install mojo` as a standalone package for enhanced Python-to-Mojo interoperability.\r\n\r\nCheck out all of 25.6's updates with the full [MAX changelog](https://docs.modular.com/max/changelog/) and [Mojo changelog](https://docs.modular.com/mojo/changelog/).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/249101992/reactions","total_count":16,"+1":3,"-1":0,"laugh":0,"hooray":1,"confused":0,"heart":0,"rocket":12,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/237713983","assets_url":"https://api.github.com/repos/modular/modular/releases/237713983/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/237713983/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/modular/v25.5.0","id":237713983,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4OKzo_","tag_name":"modular/v25.5.0","target_commitish":"modular/v25.5","name":"Modular 25.5","draft":false,"immutable":false,"prerelease":false,"created_at":"2025-08-05T15:36:57Z","updated_at":"2025-08-05T15:47:20Z","published_at":"2025-08-05T15:47:20Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/modular/v25.5.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/modular/v25.5.0","body":"Modular Platform 25.5 is [here](https://hub.docker.com/u/modular), and introduces Large Scale Batch Inference: a highly asynchronous, at-scale batch API built on open standards and powered by [Mammoth](https://www.modular.com/mammoth).\r\nThis release also features the open source launch of the MAX Graph API and expanded support for writing custom PyTorch operators directly in MAX. In addition, we’ve made Modular Platform development and deployment easier with optimized Docker containers and new standalone Mojo Conda packages. Check out all of 25.5’s updates with the full [MAX](https://docs.modular.com/max/changelog/) and [Mojo changelogs](https://docs.modular.com/mojo/changelog/).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/237713983/reactions","total_count":16,"+1":6,"-1":0,"laugh":0,"hooray":2,"confused":0,"heart":5,"rocket":3,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/226219493","assets_url":"https://api.github.com/repos/modular/modular/releases/226219493/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/226219493/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/modular/v25.4.0","id":226219493,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4Ne9Xl","tag_name":"modular/v25.4.0","target_commitish":"modular/v25.4","name":"Modular 25.4","draft":false,"immutable":false,"prerelease":false,"created_at":"2025-06-18T15:55:56Z","updated_at":"2025-06-18T16:28:42Z","published_at":"2025-06-18T15:59:07Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/modular/v25.4.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/modular/v25.4.0","body":"We're excited to announce Modular Platform 25.4, a major release that brings the full power of AMD GPUs to our entire platform. This release marks a major leap toward democratizing access to high-performance AI by enabling seamless portability to AMD GPUs. Developers can now build and deploy models optimized for peak performance, with zero reliance on any single hardware vendor—unlocking greater flexibility, lower costs, and broader access to compute.\r\n\r\nFor more details, see the [25.4 changelog](https://docs.modular.com/max/changelog#v254-2025-06-18) and the [release blog post](https://www.modular.com/blog/modular-25-4-one-container-amd-and-nvidia-gpus-no-lock-in).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/226219493/reactions","total_count":31,"+1":8,"-1":0,"laugh":0,"hooray":16,"confused":0,"heart":2,"rocket":5,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/216815009","assets_url":"https://api.github.com/repos/modular/modular/releases/216815009/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/216815009/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/modular/v25.3.0","id":216815009,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4M7FWh","tag_name":"modular/v25.3.0","target_commitish":"stable","name":"Modular 25.3","draft":false,"immutable":false,"prerelease":false,"created_at":"2025-05-07T06:39:24Z","updated_at":"2025-05-14T18:38:24Z","published_at":"2025-05-06T16:44:52Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/modular/v25.3.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/modular/v25.3.0","body":"Modular Platform's 25.3 release introduces a unified `pip install modular` package, granting access to Mojo and MAX. This release open-sources MAX Kernels and Serving APIs, totaling over 500,000 lines of code. Google Colab support is now available, enabling execution of MAX models, and a simplified community license for MAX and Mojo, aiming to lower entry barriers. This update reflects a commitment to building in the open and putting the community first.\r\n\r\nFor additional details, checkout the [changelog](https://docs.modular.com/max/changelog#v252).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/216815009/reactions","total_count":30,"+1":9,"-1":0,"laugh":0,"hooray":6,"confused":0,"heart":8,"rocket":7,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/208160990","assets_url":"https://api.github.com/repos/modular/modular/releases/208160990/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/208160990/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/max/v25.2.0","id":208160990,"author":{"login":"Ahajha","id":44127594,"node_id":"MDQ6VXNlcjQ0MTI3NTk0","avatar_url":"https://avatars.githubusercontent.com/u/44127594?v=4","gravatar_id":"","url":"https://api.github.com/users/Ahajha","html_url":"https://github.com/Ahajha","followers_url":"https://api.github.com/users/Ahajha/followers","following_url":"https://api.github.com/users/Ahajha/following{/other_user}","gists_url":"https://api.github.com/users/Ahajha/gists{/gist_id}","starred_url":"https://api.github.com/users/Ahajha/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/Ahajha/subscriptions","organizations_url":"https://api.github.com/users/Ahajha/orgs","repos_url":"https://api.github.com/users/Ahajha/repos","events_url":"https://api.github.com/users/Ahajha/events{/privacy}","received_events_url":"https://api.github.com/users/Ahajha/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4MaEje","tag_name":"max/v25.2.0","target_commitish":"stable","name":"MAX 25.2","draft":false,"immutable":false,"prerelease":false,"created_at":"2025-03-25T13:40:02Z","updated_at":"2025-03-25T15:31:42Z","published_at":"2025-03-25T15:30:55Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/max/v25.2.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/max/v25.2.0","body":"Announcing MAX 25.2, featuring significant enhancements for large-scale AI deployment and GPU optimization. This release adds comprehensive NVIDIA Hopper support with high-performance kernels, multi-GPU tensor parallelism for large models like Llama-3.3-70B, and expanded model support (Phi3, Olmo, Granite). Key additions include GPTQ quantization for memory efficiency, advanced long context optimizations (in-flight batching, chunked prefill, copy-on-write), and improved kernel caching reducing compilation times up to 28%. New Mojo GPU APIs offer developers greater control and performance.\r\n\r\nFor additional details, checkout the [changelog](https://docs.modular.com/max/changelog#v252).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/208160990/reactions","total_count":22,"+1":7,"-1":0,"laugh":0,"hooray":6,"confused":0,"heart":0,"rocket":9,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/200167482","assets_url":"https://api.github.com/repos/modular/modular/releases/200167482/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/200167482/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/max/v25.1.0","id":200167482,"author":{"login":"patrickdoc","id":1808626,"node_id":"MDQ6VXNlcjE4MDg2MjY=","avatar_url":"https://avatars.githubusercontent.com/u/1808626?v=4","gravatar_id":"","url":"https://api.github.com/users/patrickdoc","html_url":"https://github.com/patrickdoc","followers_url":"https://api.github.com/users/patrickdoc/followers","following_url":"https://api.github.com/users/patrickdoc/following{/other_user}","gists_url":"https://api.github.com/users/patrickdoc/gists{/gist_id}","starred_url":"https://api.github.com/users/patrickdoc/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/patrickdoc/subscriptions","organizations_url":"https://api.github.com/users/patrickdoc/orgs","repos_url":"https://api.github.com/users/patrickdoc/repos","events_url":"https://api.github.com/users/patrickdoc/events{/privacy}","received_events_url":"https://api.github.com/users/patrickdoc/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4L7lA6","tag_name":"max/v25.1.0","target_commitish":"stable","name":"Mojo 25.1","draft":false,"immutable":false,"prerelease":false,"created_at":"2025-02-13T16:31:46Z","updated_at":"2025-02-13T17:58:36Z","published_at":"2025-02-13T16:44:33Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/max/v25.1.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/max/v25.1.0","body":"# Release 25.1\r\n\r\nWe're excited to announce the release of MAX 25.1, marking a significant evolution in our approach to delivering cutting-edge AI development tools to our community. This release substantially improves the developer experience for Agentic and LLM workflows, introduces a new nightly release model that includes a new GPU programming interface, and launches [MAX Builds](https://builds.modular.com/) - your one-stop destination for GenAI development.\r\n\r\nFor additional details, checkout the [changelog](https://docs.modular.com/mojo/changelog/)","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/200167482/reactions","total_count":30,"+1":13,"-1":0,"laugh":0,"hooray":7,"confused":0,"heart":0,"rocket":10,"eyes":0}},{"url":"https://api.github.com/repos/modular/modular/releases/191235005","assets_url":"https://api.github.com/repos/modular/modular/releases/191235005/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/191235005/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/max/v24.6.0","id":191235005,"author":{"login":"patrickdoc","id":1808626,"node_id":"MDQ6VXNlcjE4MDg2MjY=","avatar_url":"https://avatars.githubusercontent.com/u/1808626?v=4","gravatar_id":"","url":"https://api.github.com/users/patrickdoc","html_url":"https://github.com/patrickdoc","followers_url":"https://api.github.com/users/patrickdoc/followers","following_url":"https://api.github.com/users/patrickdoc/following{/other_user}","gists_url":"https://api.github.com/users/patrickdoc/gists{/gist_id}","starred_url":"https://api.github.com/users/patrickdoc/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/patrickdoc/subscriptions","organizations_url":"https://api.github.com/users/patrickdoc/orgs","repos_url":"https://api.github.com/users/patrickdoc/repos","events_url":"https://api.github.com/users/patrickdoc/events{/privacy}","received_events_url":"https://api.github.com/users/patrickdoc/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4LZgO9","tag_name":"max/v24.6.0","target_commitish":"main","name":"Mojo 24.6","draft":false,"immutable":false,"prerelease":false,"created_at":"2024-12-17T17:05:14Z","updated_at":"2024-12-17T18:05:28Z","published_at":"2024-12-17T18:05:28Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/max/v24.6.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/max/v24.6.0","body":"# Release 24.6\r\n\r\nWe are excited to announce the release of MAX 24.6, featuring a preview of MAX GPU! At the heart of the MAX 24.6 release is MAX GPU – the first vertically integrated Generative AI serving stack that eliminates the dependency on vendor-specific computation libraries like NVIDIA’s CUDA.\r\n\r\nMAX GPU is built on two groundbreaking technologies. The first is MAX Engine, a high-performance AI model compiler and runtime built with innovative Mojo GPU kernels for NVIDIA GPUs–free from CUDA or ROCm dependencies. The second is MAX Serve, a sophisticated Python-native serving layer specifically engineered for LLM applications. MAX Serve expertly handles complex request batching and scheduling, delivering consistent and reliable performance, even under heavy workloads.\r\n\r\nFor additional details, checkout the [changelog](https://docs.modular.com/max/changelog) and the [release announcement](https://modular.com/blog/introducing-max-24-6-a-gpu-native-generative-ai-platform).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/191235005/reactions","total_count":26,"+1":8,"-1":0,"laugh":0,"hooray":8,"confused":0,"heart":0,"rocket":6,"eyes":4}},{"url":"https://api.github.com/repos/modular/modular/releases/177173084","assets_url":"https://api.github.com/repos/modular/modular/releases/177173084/assets","upload_url":"https://uploads.github.com/repos/modular/modular/releases/177173084/assets{?name,label}","html_url":"https://github.com/modular/modular/releases/tag/mojo/v24.5.0","id":177173084,"author":{"login":"patrickdoc","id":1808626,"node_id":"MDQ6VXNlcjE4MDg2MjY=","avatar_url":"https://avatars.githubusercontent.com/u/1808626?v=4","gravatar_id":"","url":"https://api.github.com/users/patrickdoc","html_url":"https://github.com/patrickdoc","followers_url":"https://api.github.com/users/patrickdoc/followers","following_url":"https://api.github.com/users/patrickdoc/following{/other_user}","gists_url":"https://api.github.com/users/patrickdoc/gists{/gist_id}","starred_url":"https://api.github.com/users/patrickdoc/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/patrickdoc/subscriptions","organizations_url":"https://api.github.com/users/patrickdoc/orgs","repos_url":"https://api.github.com/users/patrickdoc/repos","events_url":"https://api.github.com/users/patrickdoc/events{/privacy}","received_events_url":"https://api.github.com/users/patrickdoc/received_events","type":"User","user_view_type":"public","site_admin":false},"node_id":"RE_kwDOJcq7QM4Kj3Jc","tag_name":"mojo/v24.5.0","target_commitish":"61a97c6f995ed8a471d9613b908f8f5302283ac4","name":"Mojo 24.5","draft":false,"immutable":false,"prerelease":false,"created_at":"2024-09-13T17:15:06Z","updated_at":"2024-09-26T21:26:51Z","published_at":"2024-09-26T21:26:51Z","assets":[],"tarball_url":"https://api.github.com/repos/modular/modular/tarball/mojo/v24.5.0","zipball_url":"https://api.github.com/repos/modular/modular/zipball/mojo/v24.5.0","body":"# Release 24.5\r\n\r\nWe are excited to announce the release of MAX 24.5! This release includes support for installing MAX as a conda package with magic, a powerful new package and virtual environment manager. We’re also introducing two new Python APIs for MAX Graph and MAX Driver, which will ultimately provide the same low-level programming interface as the Mojo Graph API. MAX Engine has improved performance for Llama3, with 24.5 generating tokens for Llama an average of 15% to 48% faster. Lastly, this release also adds support for Python 3.12, and drops support for Python 3.8 and Ubuntu 20.04.\r\n\r\n\r\nFor additional details, checkout the [changelog](https://docs.modular.com/max/changelog) and the [release announcement](https://www.modular.com/blog/max-24-5-with-sota-cpu-performance-for-llama-3-1).","reactions":{"url":"https://api.github.com/repos/modular/modular/releases/177173084/reactions","total_count":35,"+1":16,"-1":0,"laugh":1,"hooray":6,"confused":0,"heart":7,"rocket":5,"eyes":0}}]