|
About the MAX category
|
|
0
|
190
|
December 4, 2024
|
|
MAX models can now run on Apple silicon GPUs
|
|
2
|
1545
|
July 13, 2026
|
|
First-class autodiff/training in MAX: timeline, and supersede-or-compose with community autograd libraries?
|
|
2
|
154
|
July 4, 2026
|
|
Optimized Kernels for Blackwell -- do they work on GB10
|
|
2
|
90
|
June 22, 2026
|
|
Why were FBCache and TeaCache not carried over to Flux2Executor?
|
|
0
|
74
|
May 19, 2026
|
|
Notebook format for the max-llm-book
|
|
0
|
58
|
May 15, 2026
|
|
I burned some Codex quota testing MAX training
|
|
1
|
156
|
May 13, 2026
|
|
How can I build a minimal Docker image for MAX inference
|
|
1
|
105
|
May 8, 2026
|
|
Help with max serve performance on H100
|
|
6
|
173
|
April 14, 2026
|
|
Overhead of Multi‑Dimensional Reduction
|
|
1
|
100
|
March 10, 2026
|
|
Constraint failed: copy_from_async only allows 4, 8, 16 bytes element
|
|
0
|
61
|
February 25, 2026
|
|
Help compiling MLP in MAX
|
|
4
|
124
|
February 23, 2026
|
|
Initial support for running MAX models on AMD RDNA GPUs
|
|
0
|
128
|
February 17, 2026
|
|
MAX models can now use customized Mojo kernels and standard library
|
|
0
|
124
|
February 17, 2026
|
|
Question on register custom ops for max on different device
|
|
6
|
98
|
February 13, 2026
|
|
Failed to resolve module path for `MOGGKernelAPI`
|
|
1
|
81
|
February 10, 2026
|
|
Build an LLM in MAX from scratch đź“–
|
|
10
|
758
|
February 6, 2026
|
|
All MAX API tests can now be run via Bazel in the `modular` repository
|
|
7
|
239
|
February 6, 2026
|
|
Mypy type checking workflow for new model development
|
|
2
|
103
|
January 23, 2026
|
|
Using @F.functional decorator for forward method
|
|
2
|
141
|
January 23, 2026
|
|
MAX Graph Python API built-in ops fail to compile for GPU - what's the correct pattern?
|
|
3
|
97
|
January 19, 2026
|
|
Model Correctness Check
|
|
1
|
78
|
January 14, 2026
|
|
Tensor Creation Allocates Memory on All GPUs and Fails with CUDA_VISIBLE_DEVICES
|
|
4
|
128
|
January 14, 2026
|
|
Slow tensor creation with experimental Tensor
|
|
2
|
108
|
January 12, 2026
|
|
Encoder-Decoder (T5) model serving support
|
|
4
|
224
|
January 4, 2026
|
|
Sparse Matrix/Array Formats for Roadmap Consideration 🙏
|
|
8
|
352
|
December 28, 2025
|
|
DeepSeek-OCR infer at CPU
|
|
4
|
254
|
December 22, 2025
|
|
Using max from another bazel project
|
|
1
|
104
|
December 7, 2025
|
|
MAX can now be used in Google Colab
|
|
3
|
680
|
December 4, 2025
|
|
After startup MAX server, curl access feedback "curl: (56) Recv failure: Connection reset by peer"
|
|
0
|
53
|
November 19, 2025
|