Pure Gleam tensor library with quantization (INT8, NF4, AWQ), Flash Attention, and 2:4 Sparsity - 7.5x memory multiplication
-
Updated
Jun 11, 2026 - Gleam
#
awq
Here are 2 public repositories matching this topic...
🚀 Accelerate your computations with viva_tensor, the fastest tensor library on the BEAM, designed for high-performance operations and seamless integration.
-
Updated
Jun 13, 2026 - Gleam
Improve this page
Add a description, image, and links to the awq topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the awq topic, visit your repo's landing page and select "manage topics."