DEV Community

#tpu

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Six Serving Engines on One Cloud TPU v5e Chip: Gemma 4 E2B

SGLang-JAX wins the speed test
xbill profile

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

#googlecloud #tpu #vllm #jax
14
Comments 4
12 min read
Porting Gemma 4 E2B to SGLang-JAX on One Cloud TPU v5e
xbill profile

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

#googlecloud #tpu #jax #gemma
9
Comments
10 min read
Running Captum on Cloud TPUs with TorchTPU: a work log
joinalahmed profile

Running Captum on Cloud TPUs with TorchTPU: a work log

#pytorch #tpu #machinelearning #performance
Comments
19 min read
Gemma 4 in Rust on TorchTPU: Hands On With Colab
xbill profile

Gemma 4 in Rust on TorchTPU: Hands On With Colab

#rust #pytorch #tpu #gemma
8
Comments
9 min read
Gemma 4 E2B in JAX on One TPU v5e: bf16 or 4-Bit, Python or Rust, and How It Stands Against vLLM
xbill profile

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

#jax #tpu #gemma #rust
11
Comments
10 min read
TorchTPU vs CUDA: Can Native PyTorch Make Google TPUs Easier to Use?
jamilxt profile

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

#pytorch #tpu #cuda #ai
1
Comments
8 min read
Gemma 4 in Rust on TorchTPU: A Native TPU Rig With PyO3 and MCP

Features a rare unsendable pyclass thread design
xbill profile

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

#rust #pytorch #tpu #mcp
15
Comments 3
11 min read
Google Introduces TorchTPU to Expand Access to Its AI Chips
the_daily_flare profile

Google Introduces TorchTPU to Expand Access to Its AI Chips

#google #ai #pytorch #tpu
Comments
3 min read
Space data center cooling: why Google's TPUs in orbit run 15 minutes
axrisi profile

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

#google #tpu #space #android
1
Comments
9 min read
PyTorch on TPU: Hands On With Colab
xbill profile

PyTorch on TPU: Hands On With Colab

#pytorch #tpu #gemma #googlecloud
9
Comments 1
14 min read
Inference on Google Cloud: Precision, Memory and Capacity on TPU, from v5e to Ironwood
xbill profile

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

#googlecloud #tpu #machinelearning #gemma
8
Comments 1
14 min read
Small Apache-2.0 Models Against Gemma 4 E2B on One TPU v5e: Which Ones Keep Up?

Rigorous 14 GiB TPU v5e memory budget constraints
xbill profile

Small Apache-2.0 Models Against Gemma 4 E2B on One TPU v5e: Which Ones Keep Up?

#tpu #vllm #gemma #llm
21
Comments 3
10 min read
Gemma 4 E2B in Pure JAX on a Colab TPU: Google's 4-Bit Export Against an Exact Repack

A repack beats Google's export by 342x
xbill profile

Gemma 4 E2B in Pure JAX on a Colab TPU: Google's 4-Bit Export Against an Exact Repack

#jax #tpu #gemma #machinelearning
2
Comments 4
8 min read
Deploying a QAT Checkpoint Your Serving Stack Can't Load: Gemma 4 E2B in Pure JAX on One TPU
xbill profile

Deploying a QAT Checkpoint Your Serving Stack Can't Load: Gemma 4 E2B in Pure JAX on One TPU

#tpu #jax #llm #quantization
8
Comments
10 min read
The unofficial TPU migration guide: Cloud TPU API to Compute Engine
xbill profile

The unofficial TPU migration guide: Cloud TPU API to Compute Engine

#tpu #gcp #vllm #devops
8
Comments 2
17 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.