kernels-community / megablocks

huggingface.co
Total runs: 3.4K
24-hour runs: 0
7-day runs: 565
30-day runs: 2.6K
Model's Last Updated: June 04 2026

Introduction of megablocks

Model Details of megablocks

nix develop --show-trace -i -L .#test --command python -m pytest -s tests

expected output:

============== test session starts ===============
platform linux -- Python 3.12.10, pytest-8.3.5, pluggy-1.5.0
rootdir: /home/ubuntu/Projects/megablocks-moe
plugins: hypothesis-6.130.12
collecting 43 items                              world_size=1
collected 387 items

tests/layers/moe_test.py ...........................................
tests/ops/binned_gather_test.py .....................
tests/ops/binned_scatter_test.py .....................
tests/ops/cumsum_test.py ................................
tests/ops/histogram_test.py ......................................................
tests/ops/padded_gather_test.py ......................................
tests/ops/padded_scatter_test.py ......................................................
tests/ops/replicate_test.py ..................................................................................
tests/ops/sort_test.py ..................
tests/ops/topology_test.py ....................
tests/test_mb_moe.py megablocks_moe module imported successfully.
Available functions: ['Arguments', 'MLP', 'MoE', 'ParallelDroplessMLP', 'ParallelMLP', 'SparseGLU', 'SparseMLP', '__all__', '__builtins__', '__cached__', '__doc__', '__file__', '__loader__', '__name__', '__package__', '__path__', '__spec__', '_megablocks_a4f6452_dirty', '_ops', 'argsort', 'backend', 'cumsum', 'dMoE', 'exclusive_cumsum', 'get_load_balancing_loss', 'grouped_gemm_util', 'histogram', 'inclusive_cumsum', 'indices', 'layers', 'ops', 'replicate_backward', 'replicate_forward', 'sort', 'torch']
.cumsum output: tensor([0, 1, 3, 6], device='cuda:0', dtype=torch.int16)
...

================ warnings summary ================
...
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
======= 387 passed, 18 warnings in 54.63s ========

Runs of kernels-community megablocks on huggingface.co

3.4K
Total runs
0
24-hour runs
517
3-day runs
565
7-day runs
2.6K
30-day runs

More Information About megablocks huggingface.co Model

More megablocks license Visit here:

https://choosealicense.com/licenses/apache-2.0

megablocks huggingface.co

megablocks huggingface.co is an AI model on huggingface.co that provides megablocks's model effect (), which can be used instantly with this kernels-community megablocks model. huggingface.co supports a free trial of the megablocks model, and also provides paid use of the megablocks. Support call megablocks model through api, including Node.js, Python, http.

kernels-community megablocks online free

megablocks huggingface.co is an online trial and call api platform, which integrates megablocks's modeling effects, including api services, and provides a free online trial of megablocks, you can try megablocks online for free by clicking the link below.

kernels-community megablocks online free url in huggingface.co:

https://huggingface.co/kernels-community/megablocks

megablocks install

megablocks is an open source model from GitHub that offers a free installation service, and any user can find megablocks on GitHub to install. At the same time, huggingface.co provides the effect of megablocks install, users can directly use megablocks installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

megablocks install url in huggingface.co:

https://huggingface.co/kernels-community/megablocks

Url of megablocks

Provider of megablocks huggingface.co

kernels-community
ORGANIZATIONS

Other API from kernels-community