Join the AMD Open Robotics Hackathon
•
14
None defined yet.
DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
Instella: Fully Open Language Models with Stellar Performance
Wan 2.2 14B
gpt-oss-120b on AMD MI300X GPUs
Qwen3-30B-A3B model on AMD hardware
Generate text responses in a chat interface