A package for fine-tuning Transformers with TPUs, written in Tensorflow2.0+
-
Updated
Mar 10, 2021 - Python
#
tpus
Here are 5 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-cloudattention-mechanismgemmapallasgpu-kernelstpujaxinference-optimizationtpu-benchmarkstpustpu-accelerationtrilliumkernel-optimizersvllmllm-inferencepaged-attentionsliding-window-attentionvllm-servekernel-optimizationgoodput
-
Updated
Jul 29, 2026 - Python
Train Huggingface LMs on google cloud TPUs.
-
Updated
Oct 14, 2020 - Python
Improve this page
Add a description, image, and links to the tpus topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the tpus topic, visit your repo's landing page and select "manage topics."