InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU Paper • 2502.08910 • Published 13 days ago • 141
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Paper • 2502.06703 • Published 16 days ago • 137
TransMLA: Multi-head Latent Attention Is All You Need Paper • 2502.07864 • Published 15 days ago • 44
SmolVLM 256M & 500M Collection Collection for models & demos for even smoller SmolVLM release • 12 items • Updated 6 days ago • 69