DFlash speculative decoding for Qwen3-8B on AWS Trainium2 with vLLM-Neuron; developed at NYU × Annapurna Labs Hack the Chip.
-
Updated
Oct 14, 2026 - Python
#
trainium2
Here are 2 public repositories matching this topic...
Streaming video diffusion on one AWS Trainium2 chip. StreamDiffusionV2’s causal Wan2.1 1.3B model ported to Neuron with a resident KV cache and a 4-NeuronCore layer pipeline: 5.6 → 38.4 FPS end to end, matching the CPU reference (cosine 0.99996). Plus a live SD-Turbo webcam restyle at 43.8 FPS.
pytorch streaming-video inference-optimization diffusion-models kv-cache ml-systems aws-neuron-sdk aws-neuron video-diffusion trainium streamdiffusion sd-turbo wan2-1 trainium2
-
Updated
Oct 20, 2026 - Python
Add this topic to your repo
To associate your repository with the trainium2 topic, visit your repo's landing page and select "manage topics."