DEV Community

#tpu

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Colab MCP Endpoint From Claude Code: Set It Up, Test It, Run a Notebook on a TPU

The Colab MCP Endpoint From Claude Code: Set It Up, Test It, Run a Notebook on a TPU

22
Comments 2
10 min read
Gemma 4 on a Hosted Colab TPU: The QAT Repack, Served in Two Minutes

Gemma 4 on a Hosted Colab TPU: The QAT Repack, Served in Two Minutes

19
Comments
12 min read
Running Captum on Cloud TPUs with TorchTPU: a work log

Running Captum on Cloud TPUs with TorchTPU: a work log

Comments
19 min read
Gemma 4 E2B in JAX on One TPU v5e: bf16 or 4-Bit, Python or Rust, and How It Stands Against vLLM

Gemma 4 E2B in JAX on One TPU v5e: bf16 or 4-Bit, Python or Rust, and How It Stands Against vLLM

11
Comments
10 min read
Six Serving Engines on Four Accelerators: Gemma 4 E2B on an RTX 3050, a T4, an L4 and a TPU v5e

Six Serving Engines on Four Accelerators: Gemma 4 E2B on an RTX 3050, a T4, an L4 and a TPU v5e

17
Comments 1
11 min read
Gemma 4 in Rust on TorchTPU: A Native TPU Rig With PyO3 and MCP

Features a rare unsendable pyclass thread design

Gemma 4 in Rust on TorchTPU: A Native TPU Rig With PyO3 and MCP

15
Comments 3
11 min read
Google expands TPU lineup to solve AI memory and security gaps

Google expands TPU lineup to solve AI memory and security gaps

4
Comments
4 min read
Six Serving Engines on One Cloud TPU v5e Chip: Gemma 4 E2B

SGLang-JAX wins the speed test

Six Serving Engines on One Cloud TPU v5e Chip: Gemma 4 E2B

32
Comments 5
12 min read
Porting Gemma 4 E2B to SGLang-JAX on One Cloud TPU v5e

Porting Gemma 4 E2B to SGLang-JAX on One Cloud TPU v5e

30
Comments
10 min read
Google Introduces TorchTPU to Expand Access to Its AI Chips

Google Introduces TorchTPU to Expand Access to Its AI Chips

Comments
3 min read
Space data center cooling: why Google's TPUs in orbit run 15 minutes

Space data center cooling: why Google's TPUs in orbit run 15 minutes

1
Comments
9 min read
Gemma 4 in Rust on TorchTPU: Hands On With Colab

Gemma 4 in Rust on TorchTPU: Hands On With Colab

8
Comments
9 min read
PyTorch on TPU: Hands On With Colab

PyTorch on TPU: Hands On With Colab

9
Comments 1
14 min read
Inference on Google Cloud: Precision, Memory and Capacity on TPU, from v5e to Ironwood

Inference on Google Cloud: Precision, Memory and Capacity on TPU, from v5e to Ironwood

8
Comments 1
14 min read
TorchTPU vs CUDA: Can Native PyTorch Make Google TPUs Easier to Use?

TorchTPU vs CUDA: Can Native PyTorch Make Google TPUs Easier to Use?

1
Comments
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.