Trillium is a composable toolkit for building internet applications with async rust
-
Updated
Aug 1, 2026 - Rust
#
trillium
Here are 9 public repositories matching this topic...
Measurement harness for the sliding window attention premium in the vLLM TPU Ragged Paged Attention v3 kernel: per layer decode cost, block size control, throughput, and goodput for Gemma 4 31B on TPU v6e.
google-cloud attention-mechanism gemma pallas gpu-kernels tpu jax inference-optimization tpu-benchmarks tpus tpu-acceleration trillium kernel-optimizers vllm llm-inference paged-attention sliding-window-attention vllm-serve kernel-optimization goodput
-
Updated
Jul 29, 2026 - Python
-
Updated
Jun 25, 2026 - Rust
🔢 Build and connect to a Tensor Processing Unit (TPU) VM, install PyTorch/XLA, and perform calculations efficiently for AI projects.
vm cpu gpu accelerator numpy lab torch version calculation compute tpu xla trillium tpu-software-version libopenblas-dev v6e
-
Updated
Jul 27, 2026 - Shell
tpu1 🔢🧠🖼️ : Tensor Processing Unit Demo # TPU # PyTorch # XLA # AI Hypercomputer # Google
vm cpu test gpu accelerator numpy lab torch version calculation py compute tpu xla trillium tpu-software-version libopenblas-dev v6e
-
Updated
Feb 5, 2026 - Shell
Improve this page
Add a description, image, and links to the trillium topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the trillium topic, visit your repo's landing page and select "manage topics."