Linking pages
- The Mathematics of Training LLMs — with Quentin Anthony of Eleuther AI https://www.latent.space/p/transformers-math#details 66 comments
- RWKV: Reinventing RNNs for the Transformer Era — with Eugene Cheah of UIlicious https://www.latent.space/p/rwkv#%C2%A7the-eleuther-mafia 66 comments
- The State of Silicon and the GPU Poors - with Dylan Patel of SemiAnalysis https://www.latent.space/p/semianalysis 40 comments
- LLMs Everywhere: Running 70B models in browsers and iPhones using MLC — with Tianqi Chen of CMU / OctoML https://www.latent.space/p/llms-everywhere#details 1 comment
- Cursor.so: The AI-first Code Editor — with Aman Sanger of Anysphere https://www.latent.space/p/cursor 1 comment
- The Busy Person's Intro to Finetuning & Open Source AI - Wing Lian, Axolotl https://www.latent.space/p/axolotl 0 comments
- Cloud Intelligence at the speed of 5000 tok/s - with Ce Zhang and Vipul Ved Prakash of Together AI https://www.latent.space/p/together 0 comments
Linked pages
- From Deep to Long Learning? · Hazy Research https://hazyresearch.stanford.edu/blog/2023-03-27-long-learning 124 comments
- TSMC's 3nm Node: No SRAM Scaling Implies More Expensive CPUs and GPUs | Tom's Hardware https://www.tomshardware.com/news/no-sram-scaling-implies-on-more-expensive-cpus-and-gpus 115 comments
- Petaflops to the People: from Personal Compute Cluster to Person of Compute — with George Hotz of the tiny corp https://www.latent.space/p/geohot#details 10 comments
- The Hardware Lottery https://hardwarelottery.github.io/ 9 comments
- [2205.14135] FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness https://arxiv.org/abs/2205.14135 3 comments
- Is Attention All You Need? http://www.isattentionallyouneed.com/ 0 comments
- CUTLASS 3.0 is now available! · Discussion #787 · NVIDIA/cutlass · GitHub https://github.com/NVIDIA/cutlass/discussions/787 0 comments
- Hyena Hierarchy: Towards Larger Convolutional Language Models · Hazy Research https://hazyresearch.stanford.edu/blog/2023-03-07-hyena 0 comments
- MPT-7B and The Beginning of Context=Infinity — with Jonathan Frankle and Abhinav Venigalla of MosaicML https://www.latent.space/p/mosaic-mpt-7b 0 comments
- Llama 2: The New Open LLM SOTA (ft. Nathan Lambert, Matt Bornstein, Anton Troynikov, Russell Kaplan, Whole Mars Catalog et al.) https://www.latent.space/p/llama2#details 0 comments
Related searches:
Search whole site: site:www.latent.space
Search title: FlashAttention 2: making Transformers 800% faster w/o approximation - with Tri Dao of Together AI
See how to search.