New offline logits caching and fused KL loss reduce VRAM overhead from 250GB to practical single-GPU levels, opening large-scale model compression to resource-constrained teams.
Synthesia launches interactive conversational training, positioning itself as a talent-analytics play rather than a content-generation vendor.
A new multi-part guide demystifies torch.profiler traces, starting with matrix operations and scaling to large language model optimization.
IBM's new trio of fully-dense LLMs reaches 512K-token context and outperforms a larger mixture-of-experts predecessor through rigorous data curation alone.