Skip to content

Add TornadoVM CUDA backend support and tensor-core (MMA) accelerated batch prefill (FP16 & Q8_0, Llama & Qwen3)#127

Merged
stratika merged 22 commits into
mainfrom
feat/mma_cuda
Jul 21, 2026
Merged

Add TornadoVM CUDA backend support and tensor-core (MMA) accelerated batch prefill (FP16 & Q8_0, Llama & Qwen3)#127
stratika merged 22 commits into
mainfrom
feat/mma_cuda