Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #20320

Neuron Kernel Interface (NKI)

Related event timeline, sources and context from the news index.

EVENT TIMELINE

2

CODING · 1 SOURCE · AWS Machine Learning

Train Qwen3 on AWS Trainium using torchtitan

A torchtitan walkthrough demonstrates three ways to train Qwen3 on a single AWS Trainium trn2.48xlarge: (1) via Transformers v5 backend (AutoModelForCausalLM) reading/writing Hugging Face safetensors; (2) using torchtitan’s native Qwen3Model via config.model_spec; and (3) adding NKI (Neuron Kernel Interface) mixture-of-experts kernels from torchtitan-neuron and attaching custom kernels with the override registry. The post covers environment setup (Neuron PyTorch container or AWS DL AMI), installing torchtitan-neuron, torchrun launch patterns, checkpoint loading/saving (safetensors), and reports a verified step-1 loss example for Qwen3-4B-Instruct-2507 (6.54 from published weights vs 12.43 from random init).

5.0

MODELS · 1 SOURCE · AWS Machine Learning

Deepgram ports Nova-3 speech-to-text to AWS Trainium2, gains 11–70% batch cost efficiency

Deepgram worked with AWS to port its Nova-3 speech-to-text model to AWS Trainium2, using TorchNeuron, NKILib kernels and custom Neuron kernels; the final setup runs eight model replicas on a single Amazon EC2 trn2.3xlarge instance. On Deepgram’s offline, throughput-oriented batch workloads (e.g., contact-center analytics, medical transcription) this configuration processed 11–70% more audio per dollar versus the compute options Deepgram previously used, measured using instance pricing at the time of evaluation.

7.0