DEV Community

VIDRAFT News Digest Series' Articles

Back to AI OpenFree's Series
Open Quantum Challenge: GPU-Accelerated Quantum Simulation Meets Open Benchmarking (FINAL-Bench & VIDRAFT)

Open Quantum Challenge: GPU-Accelerated Quantum Simulation Meets Open Benchmarking (FINAL-Bench & VIDRAFT)

Comments
4 min read
Training an LLM from Scratch on Inference-Only NPUs — No GPU Required

Training an LLM from Scratch on Inference-Only NPUs — No GPU Required

1
Comments
4 min read
VIDRAFT Trains a Language Model from Scratch on NPUs — No GPUs Required

VIDRAFT Trains a Language Model from Scratch on NPUs — No GPUs Required

Comments
4 min read
VKORE: LoRA Training on Inference-Only NPUs with 3.8 Inference Speedup and 0.9999 PyTorch Parity

VKORE: LoRA Training on Inference-Only NPUs with 3.8 Inference Speedup and 0.9999 PyTorch Parity

Comments
4 min read
VIDRAFT Trains a 46M-Parameter Model Entirely on Inference-Only NPUs — No CUDA Required

VIDRAFT Trains a 46M-Parameter Model Entirely on Inference-Only NPUs — No CUDA Required

Comments
4 min read
Darwin-27B-ZTC-v5 Tops the Typed Decisions Leaderboard with a 0.81 Accuracy Score

Darwin-27B-ZTC-v5 Tops the Typed Decisions Leaderboard with a 0.81 Accuracy Score

Comments
4 min read
VIDRAFT's VKORE Enables Full Model Pre-Training on Inference-Only NPUs — 0.99 Loss Correlation with GPU Baselines

VIDRAFT's VKORE Enables Full Model Pre-Training on Inference-Only NPUs — 0.99 Loss Correlation with GPU Baselines

Comments
4 min read
Darwin-180B-RSI Tops MMLU-Pro and GPQA Diamond on AIhoster's Independent Open-Model Benchmark Board

Darwin-180B-RSI Tops MMLU-Pro and GPQA Diamond on AIhoster's Independent Open-Model Benchmark Board

Comments
4 min read
VIDRAFT's FINAL-Bench Claims 11 of 44 Categories on Hugging Face's Verified Leaderboard Audit

VIDRAFT's FINAL-Bench Claims 11 of 44 Categories on Hugging Face's Verified Leaderboard Audit

Comments
3 min read