DEV Community

#jax

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Gemma 4 in Pure JAX: What Changes Between Turing and Ada, and What Doesn't

Gemma 4 in Pure JAX: What Changes Between Turing and Ada, and What Doesn't

Comments
8 min read
g5g vs g6 for LLM Serving: the Same Code, and 3.7x the Throughput

g5g vs g6 for LLM Serving: the Same Code, and 3.7x the Throughput

Comments
6 min read
Gemma 4 in Pure JAX: What Ports from TPU to GPU, and What Doesn't

Gemma 4 in Pure JAX: What Ports from TPU to GPU, and What Doesn't

6
Comments
6 min read
Deploying a QAT Checkpoint Your Serving Stack Can't Load: Gemma 4 E2B in Pure JAX on One TPU

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

8
Comments
10 min read
Large-Scale TensorCircuit Contractions on GPUs: Disabling XLA GPU Autotuning

Large-Scale TensorCircuit Contractions on GPUs: Disabling XLA GPU Autotuning

Comments
4 min read
One TPU Chip, Eight Agents: Serving Small Agent Workloads with Raw JAX

Goodput vs throughput trade-offs in agent loops

One TPU Chip, Eight Agents: Serving Small Agent Workloads with Raw JAX

11
Comments 4
15 min read
I Rewrote My RL Agent in DeepMind's Neural Network Library - Day 9 (Haiku)

I Rewrote My RL Agent in DeepMind's Neural Network Library - Day 9 (Haiku)

6
Comments 1
3 min read
PyTrees Are Not One Thing: JAX, PyTorch, and TensorFlow Compared

PyTrees Are Not One Thing: JAX, PyTorch, and TensorFlow Compared

Comments
8 min read
Why JAX Is a Much Better Backend for Quantum Circuit Simulation Than PyTorch

Why JAX Is a Much Better Backend for Quantum Circuit Simulation Than PyTorch

Comments
3 min read
You Can Now Train Quantum Signal Processing Phase Angles with Gradient Descent

You Can Now Train Quantum Signal Processing Phase Angles with Gradient Descent

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